© 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. 14278
    Prev
    Next
    INDEX
    Explanations

    instances where something is done or said unknowingly or unwittingly

    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
    739
    +0.13
    0.6%
    746
    +0.12
    0.5%
    491
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.07
    288
    +0.12
    0.06
    491
    +0.12
    0.03
    Negative Logits
    artney
    -1.03
    arching
    -0.81
    emetery
    -0.71
     Sovereign
    -0.71
     majesty
    -0.69
    onential
    -0.67
     sovereign
    -0.66
    rongh
    -0.66
    inelli
    -0.65
     Belief
    -0.65
    POSITIVE LOGITS
    nown
    0.87
    llor
    0.86
    ingly
    0.76
     unknow
    0.76
    cest
    0.75
    ster
    0.73
     Wem
    0.71
    vale
    0.71
     innoc
    0.71
     unwittingly
    0.70
    Activations Density 0.483%

    No Known Activations