© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14411
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with computing and programming

    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
    339
    +0.11
    0.5%
    141
    +0.10
    0.5%
    214
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.11
    0.01
    661
    +0.10
    0.01
    699
    +0.10
    0.01
    Negative Logits
     cand
    -0.78
     stances
    -0.71
     billboards
    -0.61
     choice
    -0.60
     ster
    -0.59
     proportions
    -0.59
     amplitude
    -0.59
     expectations
    -0.58
     contemplation
    -0.58
     intensity
    -0.57
    POSITIVE LOGITS
     Paste
    0.89
    RAW
    0.88
    INGS
    0.87
    LER
    0.83
    Rated
    0.82
    ORS
    0.79
    ERSON
    0.76
     EDITION
    0.75
     Edited
    0.73
    Untitled
    0.72
    Activations Density 0.015%

    No Known Activations