© 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. 35028
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues and humanitarian concerns

    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%
    288
    +0.13
    0.7%
    583
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.27
    0.19
    377
    +0.13
    0.17
    224
    +0.12
    0.11
    Negative Logits
    raph
    -0.59
    Bey
    -0.59
    RECT
    -0.56
    abet
    -0.56
    ockey
    -0.55
     Gillespie
    -0.54
    urations
    -0.53
    FU
    -0.53
    acc
    -0.53
     FEC
    -0.52
    POSITIVE LOGITS
    ankind
    0.82
     beings
    0.80
    zee
    0.67
    arily
    0.66
     bom
    0.63
     inhab
    0.63
    mite
    0.62
    geist
    0.62
    ÃŃs
    0.61
    idis
    0.61
    Activations Density 7.115%

    No Known Activations