© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31166
    Prev
    Next
    INDEX
    Explanations

    references to violent or destructive events, conflicts, and attacks in various contexts

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.19
    1.0%
    376
    +0.08
    0.4%
    553
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.27
    393
    +0.08
    0.39
    385
    +0.07
    0.27
    Negative Logits
    soDeliveryDate
    -0.63
    bet
    -0.61
    ãĤ´ãĥ³
    -0.60
    é¾įå
    -0.58
    utical
    -0.58
    soType
    -0.58
    VPN
    -0.57
    tek
    -0.56
     wrinkles
    -0.56
    Craft
    -0.55
    POSITIVE LOGITS
     civilians
    0.78
     unarmed
    0.73
     targets
    0.65
     civilian
    0.65
     innocent
    0.63
    itals
    0.61
     unsuspecting
    0.60
     spree
    0.60
     target
    0.60
     prey
    0.59
    Activations Density 18.499%

    No Known Activations