© 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. 14420
    Prev
    Next
    INDEX
    Explanations

    terms related to racial segregation and civil rights issues

    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
    57
    +0.14
    0.5%
    365
    +0.12
    0.4%
    70
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.21
    57
    +0.12
    0.09
    346
    +0.12
    0.09
    Negative Logits
    sis
    -0.98
    ronic
    -0.89
    eger
    -0.89
    ANGE
    -0.87
    amina
    -0.85
    GROUP
    -0.85
    rative
    -0.83
    hab
    -0.82
    eq
    -0.82
    angers
    -0.81
    POSITIVE LOGITS
     Protestants
    0.97
     hust
    0.94
     gin
    0.89
     stripes
    0.89
     gau
    0.85
     Protestant
    0.84
    boats
    0.84
     widow
    0.83
     Doodle
    0.83
     blacks
    0.82
    Activations Density 3.241%

    No Known Activations