© 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. 830
    Prev
    Next
    INDEX
    Explanations

    differences or distinctions between various 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
    393
    +0.29
    1.0%
    608
    +0.17
    0.6%
    296
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    692
    +0.29
    0.06
    647
    +0.17
    0.07
    608
    +0.14
    0.09
    Negative Logits
    roll
    -0.94
    Bern
    -0.93
    azz
    -0.92
    tti
    -0.92
    iverse
    -0.92
    inet
    -0.90
    anced
    -0.90
    icago
    -0.90
    whe
    -0.87
    Bah
    -0.87
    POSITIVE LOGITS
     ours
    1.23
    lihood
    1.07
     what
    0.97
    otin
    0.89
     those
    0.88
     hers
    0.83
     anything
    0.83
     [+
    0.81
     usual
    0.80
     our
    0.80
    Activations Density 1.048%

    No Known Activations