© 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. 35445
    Prev
    Next
    INDEX
    Explanations

    instructions relating to clicking on specific elements in a digital interface to perform actions or make selections

    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
    71
    +0.11
    0.6%
    70
    +0.09
    0.5%
    708
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.11
    255
    +0.09
    0.09
    442
    +0.08
    0.07
    Negative Logits
    seys
    -0.69
    6666
    -0.68
    POST
    -0.66
    WR
    -0.56
    PASS
    -0.55
    league
    -0.54
    fam
    -0.51
    mand
    -0.51
    Sov
    -0.51
    Met
    -0.51
    POSITIVE LOGITS
    enegger
    0.72
    nir
    0.64
    phrine
    0.57
    arna
    0.57
    able
    0.55
    etsy
    0.54
    uran
    0.54
    uda
    0.54
    alysed
    0.53
    ignty
    0.53
    Activations Density 9.016%

    No Known Activations