© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14379
    Prev
    Next
    INDEX
    Explanations

    the word "resume" in various contexts

    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
    288
    +0.14
    0.6%
    271
    +0.13
    0.5%
    734
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.06
    271
    +0.13
    0.04
    531
    +0.13
    0.04
    Negative Logits
    ahi
    -0.75
     yea
    -0.74
    !/
    -0.70
    Jr
    -0.70
    bi
    -0.69
     amen
    -0.69
    boy
    -0.66
     Tribune
    -0.66
    tar
    -0.66
    LGBT
    -0.65
    POSITIVE LOGITS
    prisingly
    0.90
    prise
    0.83
     hemor
    0.82
     Canaver
    0.82
     composure
    0.79
    prises
    0.78
    ignty
    0.76
    prising
    0.76
     regained
    0.75
    chwitz
    0.75
    Activations Density 0.449%

    No Known Activations