© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31947
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to social structures and political philosophy

    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
    +0.27
    1.4%
    393
    +0.12
    0.6%
    459
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.27
    -0.26
    138
    +0.12
    0.18
    447
    +0.08
    0.21
    Negative Logits
    ovych
    -0.75
     largeDownload
    -0.65
    fast
    -0.59
    uty
    -0.57
    ileaks
    -0.56
    rious
    -0.54
    ighters
    -0.53
     Accessed
    -0.53
     Rebell
    -0.53
    aird
    -0.53
    POSITIVE LOGITS
    pless
    0.77
     practise
    0.73
     encompass
    0.68
     practice
    0.67
     Practice
    0.64
     mainland
    0.61
     impart
    0.58
     compensate
    0.57
     apply
    0.57
     maximize
    0.57
    Activations Density 15.457%

    No Known Activations