© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3551
    Prev
    Next
    INDEX
    Explanations

    specific named entities related to luxury cars, airlines, political figures, and companies

    oai_token-act-pair · gpt-3.5-turbo
    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
    171
    +0.14
    0.5%
    663
    +0.12
    0.5%
    590
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.14
    0.13
    288
    +0.12
    0.16
    481
    +0.12
    0.16
    Negative Logits
    nown
    -0.77
    pmwiki
    -0.77
     imped
    -0.76
    =/
    -0.75
    )=
    -0.72
    ãĥ£
    -0.71
     mismatch
    -0.70
    ories
    -0.69
    abases
    -0.69
    rss
    -0.68
    POSITIVE LOGITS
    's
    0.93
    HQ
    0.90
     himself
    0.86
     HQ
    0.83
    ÃŃs
    0.83
     herself
    0.80
    ÃŃa
    0.77
    aer
    0.76
    tsy
    0.75
    Own
    0.74
    Activations Density 2.712%

    No Known Activations