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

    Neuronpedia

    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. 13870
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications of products, specifically focusing on features and upgrades

    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
    196
    +0.13
    0.6%
    475
    +0.09
    0.4%
    166
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.02
    488
    +0.09
    0.13
    675
    +0.09
    0.10
    Negative Logits
    ships
    -0.65
     Kurds
    -0.64
    birds
    -0.63
    wordpress
    -0.62
    zees
    -0.60
     Turks
    -0.60
    skirts
    -0.60
     Rou
    -0.59
    zee
    -0.58
    Turkey
    -0.58
    POSITIVE LOGITS
    PLA
    0.91
    LP
    0.71
    osher
    0.69
    382
    0.69
    igslist
    0.68
    unction
    0.66
    onis
    0.66
    âĢ²
    0.66
    rm
    0.65
    vation
    0.64
    Activations Density 8.094%

    No Known Activations