© 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 EvalsExportsinterp-engineNEWAPI 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. 36749
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and product development

    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
    +0.34
    1.4%
    679
    +0.18
    0.7%
    288
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.34
    0.06
    461
    +0.18
    0.07
    679
    +0.13
    0.12
    Negative Logits
    laus
    -0.77
    CLASSIFIED
    -0.77
     Nights
    -0.71
    âĸ¬
    -0.71
    roe
    -0.69
    asons
    -0.68
     Tale
    -0.68
     Brother
    -0.67
     Deck
    -0.67
    bage
    -0.66
    POSITIVE LOGITS
    ivity
    1.27
    ively
    1.25
     packaging
    0.99
    iveness
    0.95
    ivities
    0.93
    kit
    0.88
    rador
    0.86
    Products
    0.82
     products
    0.82
     marketed
    0.82
    Activations Density 5.311%

    No Known Activations