© 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. 8586
    Prev
    Next
    INDEX
    Explanations

    scientific and mathematical terms or formulas

    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
    153
    +0.14
    0.6%
    699
    +0.14
    0.6%
    587
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.15
    232
    +0.14
    0.10
    288
    +0.13
    0.16
    Negative Logits
    inav
    -1.01
    MAT
    -0.88
    aic
    -0.87
    teenth
    -0.86
    cence
    -0.85
    ussen
    -0.84
     midterm
    -0.82
    holders
    -0.82
    NetMessage
    -0.81
    hesion
    -0.81
    POSITIVE LOGITS
    ãĤ¡
    1.03
    âĸĪ
    0.99
    aries
    0.97
    er
    0.93
    naire
    0.90
    ary
    0.87
    Ĥİ
    0.85
    eer
    0.85
    ality
    0.83
    ese
    0.80
    Activations Density 3.506%

    No Known Activations