© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12408
    Prev
    Next
    INDEX
    Explanations

    HTML tags from a document, specifically identifying attributes like names, values, ids, and classes

    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
    425
    +0.08
    0.4%
    523
    +0.08
    0.4%
    340
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.08
    0.01
    586
    +0.08
    0.01
    373
    +0.08
    -0.01
    Negative Logits
    å£
    -0.71
    crow
    -0.68
    shit
    -0.65
    åº
    -0.63
    ones
    -0.60
    phy
    -0.59
    haar
    -0.58
    Pure
    -0.56
    otal
    -0.56
    mix
    -0.56
    POSITIVE LOGITS
     Townsend
    0.57
     assurances
    0.56
     Podesta
    0.53
     Polk
    0.53
    etta
    0.52
    Graham
    0.52
    ategic
    0.51
     rapport
    0.51
     respond
    0.51
     Carlson
    0.51
    Activations Density 0.036%

    No Known Activations