© 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. 6040
    Prev
    Next
    INDEX
    Explanations

    references to articles, volumes, and page numbers

    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
    699
    +0.10
    0.4%
    211
    +0.10
    0.4%
    638
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.10
    0.02
    175
    +0.10
    0.01
    514
    +0.09
    0.02
    Negative Logits
    riad
    -0.88
    Introduced
    -0.84
    erella
    -0.78
    cham
    -0.76
    eeks
    -0.72
    negie
    -0.68
    ihad
    -0.67
    chuk
    -0.67
    orno
    -0.66
    cause
    -0.66
    POSITIVE LOGITS
    wagen
    1.08
    §
    0.86
    theme
    0.82
    ³
    0.81
    ĨĴ
    0.80
    etric
    0.78
    Ń·
    0.75
    ¸
    0.75
    Ŀ
    0.73
    ĺ
    0.71
    Activations Density 0.168%

    No Known Activations