© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7590
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between different entities or concepts

    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
    509
    +0.14
    0.6%
    675
    +0.13
    0.5%
    564
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.03
    97
    +0.13
    0.02
    299
    +0.12
    0.02
    Negative Logits
    umenthal
    -0.95
    itsch
    -0.94
    wig
    -0.89
    riz
    -0.89
    inen
    -0.88
    cci
    -0.88
    vp
    -0.87
    linger
    -0.87
    ijk
    -0.86
    ossier
    -0.86
    POSITIVE LOGITS
     CHRIST
    0.91
    FACE
    0.90
    CLASSIFIED
    0.86
    pecting
    0.85
    illes
    0.84
    âĸ¬
    0.82
    pects
    0.82
    lihood
    0.77
     Clause
    0.77
    ãĥĨãĤ£
    0.75
    Activations Density 0.147%

    No Known Activations