© 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. 33635
    Prev
    Next
    INDEX
    Explanations

    scientific research-related terms and data

    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
    +0.11
    0.6%
    482
    +0.09
    0.5%
    127
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.29
    640
    +0.09
    0.24
    127
    +0.09
    0.08
    Negative Logits
    istry
    -0.59
     fencing
    -0.53
     nationalists
    -0.52
     drowning
    -0.51
     bleeding
    -0.51
     whales
    -0.50
     nationalism
    -0.49
     thinking
    -0.49
    sed
    -0.48
     pastoral
    -0.48
    POSITIVE LOGITS
    120
    0.71
    134
    0.67
    200
    0.67
    162
    0.66
    113
    0.65
    114
    0.65
    148
    0.65
    145
    0.65
    146
    0.64
    194
    0.63
    Activations Density 13.222%

    No Known Activations