Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34660
    Prev
    Next
    INDEX
    Explanations

    Nvidia graphics card models and technical specifications

    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
    +0.14
    0.7%
    326
    +0.12
    0.6%
    365
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.19
    201
    +0.12
    0.08
    415
    +0.11
    0.06
    Negative Logits
    actor
    -0.69
    assic
    -0.67
    uden
    -0.64
    zag
    -0.62
     eclipse
    -0.58
    hood
    -0.56
    undown
    -0.56
    ardy
    -0.54
    axy
    -0.54
    ussia
    -0.54
    POSITIVE LOGITS
    80
    0.89
    211
    0.78
    itement
    0.75
    uador
    0.75
    ivil
    0.68
    swick
    0.68
    eenth
    0.68
    olver
    0.67
    70
    0.67
    30
    0.65
    Activations Density 6.648%

    No Known Activations