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

    Neuronpedia

    Jacobian LensNEW
    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. 33686
    Prev
    Next
    INDEX
    Explanations

    descriptions of changes in a situation compared to a previous state

    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
    512
    +0.17
    0.7%
    393
    +0.12
    0.5%
    516
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.17
    0.18
    566
    +0.12
    0.16
    502
    +0.10
    0.13
    Negative Logits
     Christy
    -0.71
     Fine
    -0.69
    urai
    -0.65
     Brig
    -0.64
     Vine
    -0.64
     Lieutenant
    -0.63
     reinforcement
    -0.61
     Lt
    -0.60
     Delicious
    -0.59
     Byr
    -0.59
    POSITIVE LOGITS
    ago
    0.90
    usual
    0.86
     imagined
    0.84
    fters
    0.80
     ourselves
    0.80
     usual
    0.80
     ever
    0.79
     ordinarily
    0.78
     herself
    0.76
     intended
    0.75
    Activations Density 8.333%

    No Known Activations