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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33009
    Prev
    Next
    INDEX
    Explanations

    mentions of community activities and services aimed at youth in various contexts

    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
    +0.19
    0.9%
    288
    +0.17
    0.9%
    718
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.19
    0.09
    294
    +0.17
    0.02
    721
    +0.12
    0.06
    Negative Logits
    aeda
    -0.74
    pard
    -0.73
    ãĤ´ãĥ³
    -0.70
    essen
    -0.67
    ++++++++++++++++
    -0.67
    rary
    -0.66
    igslist
    -0.66
    ertodd
    -0.66
    ×Ļ×
    -0.65
    uments
    -0.64
    POSITIVE LOGITS
    fulness
    1.08
    fully
    0.73
     academy
    0.71
    ULT
    0.71
    doms
    0.69
    bands
    0.68
    ful
    0.67
    life
    0.65
    uates
    0.64
    NT
    0.63
    Activations Density 8.783%

    No Known Activations