© 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. 3460
    Prev
    Next
    INDEX
    Explanations

    verbs related to attempting or experimenting

    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
    659
    +0.14
    0.5%
    652
    +0.14
    0.5%
    641
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.14
    0.06
    282
    +0.14
    0.05
    212
    +0.13
    0.05
    Negative Logits
    dylib
    -1.02
    edly
    -0.96
    hip
    -0.95
    head
    -0.94
    Rated
    -0.93
    models
    -0.92
    ificantly
    -0.92
    scar
    -0.91
    lav
    -0.91
    Plot
    -0.91
    POSITIVE LOGITS
     unsuccessfully
    1.43
     desperately
    1.04
     harder
    1.01
    ichick
    0.99
     luck
    0.91
    ggle
    0.91
    nir
    0.88
    onies
    0.86
    ange
    0.85
    enged
    0.85
    Activations Density 0.494%

    No Known Activations