© 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. 5610
    Prev
    Next
    INDEX
    Explanations

    Proper names or entities that may be related to a variety of subjects or individuals

    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
    706
    +0.18
    0.6%
    398
    +0.15
    0.5%
    442
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.07
    398
    +0.15
    0.07
    701
    +0.15
    0.06
    Negative Logits
     tremend
    -0.99
     seiz
    -0.98
    Ļ½
    -0.96
    ij士
    -0.95
    CLASSIFIED
    -0.94
     carbohyd
    -0.94
    PDATE
    -0.92
     skim
    -0.92
    ©¶æ¥µ
    -0.91
     incarceration
    -0.91
    POSITIVE LOGITS
    inki
    1.34
    oad
    1.19
    abo
    1.18
    igham
    1.14
    ote
    1.12
    mony
    1.10
    host
    1.10
    hare
    1.10
    ails
    1.08
    idad
    1.06
    Activations Density 1.806%

    No Known Activations