© 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. 12589
    Prev
    Next
    INDEX
    Explanations

    descriptions related to technical processes or implications

    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
    +0.29
    1.4%
    250
    +0.10
    0.4%
    362
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.29
    0.10
    362
    +0.10
    0.10
    250
    +0.09
    0.08
    Negative Logits
    nee
    -0.76
    few
    -0.71
    pload
    -0.71
    igue
    -0.70
    dayName
    -0.68
    monton
    -0.66
    keys
    -0.65
    auga
    -0.63
    ÅĤ
    -0.63
    uristic
    -0.62
    POSITIVE LOGITS
     our
    0.85
     course
    0.82
     sorts
    0.80
     humankind
    0.78
     ours
    0.78
     mankind
    0.75
     life
    0.74
     OUR
    0.73
     these
    0.72
     the
    0.71
    Activations Density 1.497%

    No Known Activations