© 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. 12902
    Prev
    Next
    INDEX
    Explanations

    references to locations or organizations related to security or governmental agencies

    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
    385
    +0.13
    0.7%
    288
    +0.11
    0.6%
    116
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.13
    0.09
    577
    +0.11
    0.09
    683
    +0.10
    0.08
    Negative Logits
    merce
    -0.71
     bom
    -0.65
    itsch
    -0.63
    tics
    -0.61
     condemned
    -0.58
     brim
    -0.58
     twe
    -0.54
    mercial
    -0.53
     Hemp
    -0.52
     seiz
    -0.52
    POSITIVE LOGITS
    eties
    0.79
    uary
    0.77
    Secret
    0.77
     Agents
    0.75
     Secret
    0.72
    ariat
    0.70
     Keeper
    0.69
     Guard
    0.68
     Armory
    0.67
     Deposit
    0.66
    Activations Density 4.933%

    No Known Activations