© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6035
    Prev
    Next
    INDEX
    Explanations

    information related to items, descriptions, or characteristics of objects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.53
    1.8%
    608
    +0.24
    0.8%
    381
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.53
    0.15
    608
    +0.24
    0.16
    393
    +0.17
    0.14
    Negative Logits
    heit
    -1.01
     thereof
    -0.97
    ume
    -0.96
    âĢİ
    -0.96
    iture
    -0.96
    SPONSORED
    -0.95
    Allows
    -0.95
    lean
    -0.95
    Change
    -0.93
    ²
    -0.93
    POSITIVE LOGITS
     earliest
    1.67
     largest
    1.54
     aforementioned
    1.54
     highest
    1.48
     finest
    1.45
     greatest
    1.45
     heaviest
    1.43
     smallest
    1.42
     biggest
    1.41
     strongest
    1.40
    Activations Density 2.806%

    No Known Activations