© 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. 39945
    Prev
    Next
    INDEX
    Explanations

    technical terms related to medical conditions and treatments

    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
    99
    +0.04
    0.5%
    200
    +0.04
    0.5%
    429
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.04
    0.25
    288
    +0.04
    0.25
    99
    +0.04
    0.12
    Negative Logits
     discipline
    -0.29
    onest
    -0.28
    otropic
    -0.27
    acion
    -0.27
    wal
    -0.25
    club
    -0.24
    Focus
    -0.23
     Boards
    -0.23
    olla
    -0.23
     Polo
    -0.23
    POSITIVE LOGITS
    cious
    0.34
    ciating
    0.33
    sembly
    0.31
    iership
    0.30
    ulhu
    0.29
    auri
    0.29
    nown
    0.28
    cius
    0.28
    NetMessage
    0.28
    etooth
    0.28
    Activations Density 9.657%

    No Known Activations