© 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. 865
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms or concepts, potentially related to analytical or critical discussions

    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
    195
    +0.17
    0.6%
    116
    +0.14
    0.5%
    549
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.07
    288
    +0.14
    0.08
    232
    +0.14
    0.04
    Negative Logits
    rek
    -0.98
     Nationwide
    -0.89
    tan
    -0.82
    shock
    -0.81
    ramid
    -0.80
    yre
    -0.79
     Leban
    -0.79
     Pens
    -0.79
     Sheen
    -0.78
     LCS
    -0.78
    POSITIVE LOGITS
    cture
    1.34
    emate
    1.23
    eties
    1.17
    wart
    1.05
    eteenth
    1.00
    eness
    0.94
    iet
    0.91
    iery
    0.91
    estro
    0.90
     junction
    0.89
    Activations Density 0.796%

    No Known Activations