© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10257
    Prev
    Next
    INDEX
    Explanations

    information related to shootings, gunmen, suspects, victims, gunmen's actions, police response, and details surrounding violent incidents

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.18
    0.6%
    590
    +0.15
    0.5%
    145
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.09
    346
    +0.15
    0.07
    32
    +0.14
    0.07
    Negative Logits
    é¾
    -1.14
    é£
    -1.06
    Balt
    -1.02
    0200
    -0.96
    ç«
    -0.96
    galitarian
    -0.95
    Mount
    -0.94
    BuyableInstoreAndOnline
    -0.91
    fork
    -0.91
    Intern
    -0.90
    POSITIVE LOGITS
     gunman
    1.24
     suspects
    1.20
     suspect
    1.09
    nels
    1.08
     bomber
    1.08
     shooter
    1.08
    hunt
    1.05
     spree
    1.05
     rapist
    1.04
     gunned
    1.02
    Activations Density 1.039%

    No Known Activations