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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3849
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and concepts

    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
    153
    +0.02
    0.5%
    56
    +0.02
    0.5%
    546
    +0.01
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.02
    0.02
    100
    +0.02
    0.02
    268
    +0.01
    0.01
    Negative Logits
    Ward
    -0.12
    uminati
    -0.11
    inals
    -0.11
    rawdownloadcloneembedreportprint
    -0.11
    Members
    -0.11
    atos
    -0.11
    PF
    -0.11
    IDA
    -0.11
    governmental
    -0.11
    tan
    -0.11
    POSITIVE LOGITS
     Rampage
    0.16
     shenan
    0.13
     WATCHED
    0.13
     earthqu
    0.13
     bark
    0.12
    ãĥ¤
    0.12
     millenn
    0.12
     Scream
    0.11
     landsl
    0.11
    interstitial
    0.11
    Activations Density 0.118%

    No Known Activations