© 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. 13574
    Prev
    Next
    INDEX
    Explanations

    events or actions related to criminal activities or conflicts

    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
    393
    +0.28
    1.3%
    587
    +0.13
    0.6%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.28
    0.17
    43
    +0.13
    0.16
    765
    +0.11
    0.15
    Negative Logits
    arah
    -0.71
    isi
    -0.70
    ument
    -0.69
    herent
    -0.69
    ulz
    -0.67
    smanship
    -0.66
    ongevity
    -0.66
    iple
    -0.65
    ety
    -0.64
    opia
    -0.64
    POSITIVE LOGITS
     namely
    1.00
     preferably
    0.99
     whence
    0.96
     albeit
    0.95
     presumably
    0.94
     which
    0.86
     although
    0.85
     wherein
    0.82
     where
    0.81
     whereas
    0.80
    Activations Density 3.487%

    No Known Activations