© 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. 13445
    Prev
    Next
    INDEX
    Explanations

    text related to legal matters and regulations

    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
    48
    +0.13
    0.6%
    151
    +0.11
    0.5%
    6
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.13
    0.18
    48
    +0.11
    0.17
    6
    +0.10
    0.14
    Negative Logits
     shape
    -0.77
    geries
    -0.76
     undecided
    -0.75
     masse
    -0.74
     resemblance
    -0.74
     imagination
    -0.74
     puff
    -0.72
     orgasm
    -0.72
    anguage
    -0.72
    cember
    -0.71
    POSITIVE LOGITS
    cue
    0.95
     Similarly
    0.93
    âĢ¢âĢ¢
    0.92
    tab
    0.89
    SourceFile
    0.88
    âģ
    0.88
    âĢł
    0.87
    said
    0.87
    sbm
    0.85
    Sah
    0.85
    Activations Density 1.179%

    No Known Activations