© 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. 33012
    Prev
    Next
    INDEX
    Explanations

    phrases related to health care and medical treatment

    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
    393
    +0.23
    1.1%
    447
    +0.17
    0.8%
    665
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.23
    0.24
    718
    +0.17
    0.21
    665
    +0.14
    0.21
    Negative Logits
    grain
    -0.67
    illin
    -0.65
    hent
    -0.64
    listed
    -0.64
     largeDownload
    -0.63
     Lots
    -0.61
    _.
    -0.60
     quotations
    -0.59
    ¼
    -0.59
    cheon
    -0.58
    POSITIVE LOGITS
     achieve
    1.15
     avoid
    1.07
     pursue
    1.06
     fulfill
    1.06
     accomplish
    1.05
     engage
    1.04
     defend
    1.03
     maximize
    1.01
     reach
    1.01
     acquire
    1.01
    Activations Density 8.815%

    No Known Activations