© 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. 14259
    Prev
    Next
    INDEX
    Explanations

    scientific and academic references, as well as technical details and specifications

    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
    300
    +0.12
    0.5%
    481
    +0.11
    0.4%
    552
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    640
    +0.11
    0.02
    511
    +0.10
    0.01
    Negative Logits
     newsp
    -0.89
    SPA
    -0.78
     Chatt
    -0.75
     Adin
    -0.73
     snippets
    -0.70
     Sard
    -0.69
     Newsp
    -0.68
     millenn
    -0.67
    ypes
    -0.66
     uploading
    -0.65
    POSITIVE LOGITS
    cko
    0.76
    Reviewed
    0.74
    Rated
    0.74
    amic
    0.71
    escal
    0.69
    aneers
    0.68
    keye
    0.67
    arium
    0.67
    izo
    0.66
     embodied
    0.66
    Activations Density 0.059%

    No Known Activations