© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1673
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to media and politics

    oai_token-act-pair · gpt-3.5-turbo

    names of news anchors or hosts and related keywords emphasizing broadcasting or media appearances

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    162
    +0.13
    0.5%
    6
    +0.13
    0.5%
    725
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.13
    0.07
    76
    +0.13
    0.08
    346
    +0.12
    0.07
    Negative Logits
    agna
    -0.88
    esa
    -0.79
    ntil
    -0.79
    heon
    -0.77
    urat
    -0.76
    activation
    -0.76
    ulkan
    -0.75
    ettel
    -0.74
     specification
    -0.74
    arcity
    -0.74
    POSITIVE LOGITS
     aired
    1.59
     airs
    1.49
     broadcasts
    1.48
     airing
    1.48
     television
    1.42
     broadcast
    1.35
     TV
    1.32
     tv
    1.31
     commercials
    1.30
     Hannity
    1.29
    Activations Density 3.724%

    No Known Activations