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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 31791
    Prev
    Next
    INDEX
    Explanations

    details related to fatal incidents involving shootings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    601
    +0.11
    0.5%
    447
    +0.10
    0.5%
    47
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.15
    486
    +0.10
    0.03
    686
    +0.10
    0.05
    Negative Logits
    hist
    -0.83
    wcsstore
    -0.79
     stru
    -0.71
    dan
    -0.71
    DragonMagazine
    -0.68
     estab
    -0.67
    odder
    -0.65
    ertain
    -0.65
    pmwiki
    -0.64
    arist
    -0.64
    POSITIVE LOGITS
     spree
    0.89
     Trayvon
    0.78
     Sandra
    0.77
     gunshot
    0.76
     rampage
    0.71
     EMS
    0.70
     fatally
    0.69
     stabbing
    0.69
     gunned
    0.68
     bystanders
    0.68
    Activations Density 9.001%

    No Known Activations