© 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. 7886
    Prev
    Next
    INDEX
    Explanations

    complex or abstract concepts related to morality or civilization

    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
    552
    +0.04
    0.5%
    688
    +0.04
    0.4%
    539
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.04
    -0.01
    581
    +0.04
    0.02
    404
    +0.04
    0.02
    Negative Logits
    QUI
    -0.34
     Bian
    -0.30
     jumper
    -0.27
    Crash
    -0.27
     Pace
    -0.26
     understatement
    -0.26
     joke
    -0.26
     Butt
    -0.26
     quieter
    -0.25
     Dynam
    -0.25
    POSITIVE LOGITS
    ipment
    0.35
    istration
    0.33
    orage
    0.33
    loads
    0.32
    >(
    0.32
    aled
    0.32
    owship
    0.32
    eat
    0.32
    arcity
    0.31
    ome
    0.31
    Activations Density 0.056%

    No Known Activations