© 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 Local
    9. 6-RES_SCL-AJT
    11. 32711
    Prev
    Next
    INDEX
    Explanations

    phrases related to civil rights

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.25
    1.1%
    288
    +0.11
    0.5%
    110
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.20
    709
    +0.11
    0.12
    575
    +0.10
    0.14
    Negative Logits
    ãĤ¨ãĥ«
    -0.82
    66666666
    -0.78
    jad
    -0.76
    Rot
    -0.74
    hap
    -0.73
    uckland
    -0.72
    Downloadha
    -0.69
    awar
    -0.69
    20439
    -0.67
    random
    -0.67
    POSITIVE LOGITS
     pamph
    0.86
     era
    0.76
     bureau
    0.75
     icon
    0.73
     anthem
    0.72
     organizations
    0.71
     workers
    0.71
     insur
    0.70
     attorney
    0.70
     initiatives
    0.68
    Activations Density 7.413%

    No Known Activations