© 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. 33661
    Prev
    Next
    INDEX
    Explanations

    information or recommendations about activities, experiences, or places

    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
    +0.31
    1.4%
    718
    +0.17
    0.8%
    393
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.31
    0.22
    608
    +0.17
    0.23
    49
    +0.14
    0.15
    Negative Logits
    soDeliveryDate
    -0.75
    riot
    -0.62
    ienne
    -0.58
    riots
    -0.57
    nexus
    -0.57
    hops
    -0.57
     viruses
    -0.56
    typ
    -0.56
     surges
    -0.56
     signals
    -0.55
    POSITIVE LOGITS
    ggles
    1.20
    wered
    1.03
    ppers
    1.02
     cherish
    1.02
    pper
    0.98
     satisfy
    0.92
     contend
    0.92
     maximize
    0.92
     give
    0.92
     achieve
    0.91
    Activations Density 11.388%

    No Known Activations