© 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. 39923
    Prev
    Next
    INDEX
    Explanations

    information related to medical treatments, trials, and physical effects on the body

    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
    +0.20
    0.8%
    395
    +0.13
    0.5%
    68
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.20
    0.07
    289
    +0.13
    -0.04
    461
    +0.11
    0.07
    Negative Logits
    comed
    -0.95
    mp
    -0.92
    asper
    -0.78
    hel
    -0.78
    cro
    -0.77
    fol
    -0.76
    rop
    -0.76
    accompan
    -0.76
    hak
    -0.75
    ask
    -0.75
    POSITIVE LOGITS
     2
    1.14
     XVI
    1.13
     XII
    1.13
     1
    1.01
     XIV
    0.99
     3
    0.98
     VII
    0.97
     II
    0.97
     XI
    0.96
    2
    0.95
    Activations Density 14.451%

    No Known Activations