© 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. 35376
    Prev
    Next
    INDEX
    Explanations

    terms related to critical evaluation and analysis, particularly focusing on important components or issues

    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
    +0.19
    0.8%
    377
    +0.12
    0.5%
    8
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.19
    0.09
    381
    +0.12
    0.08
    616
    +0.12
    0.06
    Negative Logits
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.87
    UAL
    -0.84
    boat
    -0.84
    owship
    -0.83
    Haunted
    -0.81
    bows
    -0.80
    ILA
    -0.78
    boats
    -0.78
    Pic
    -0.78
    uated
    -0.77
    POSITIVE LOGITS
     importance
    0.94
    arial
    0.88
     acclaim
    0.87
     components
    0.84
     Role
    0.83
     appraisal
    0.81
    ostic
    0.80
     jun
    0.80
    erion
    0.79
     thinkers
    0.79
    Activations Density 5.510%

    No Known Activations