© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    instances where a character in a story almost or nearly experiences a significant event or action

    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
    718
    +0.18
    0.6%
    297
    +0.12
    0.4%
    130
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.18
    0.05
    214
    +0.12
    0.03
    313
    +0.12
    0.03
    Negative Logits
    nation
    -1.14
    sheet
    -1.04
    ysis
    -1.00
    city
    -1.00
     Dynamics
    -1.00
    voc
    -0.99
    held
    -0.98
     è£ıè¦ļéĨĴ
    -0.96
    Reviewer
    -0.96
    illary
    -0.96
    POSITIVE LOGITS
     spoil
    1.13
     accidentally
    1.01
     succeeded
    1.01
     ruined
    1.00
     exha
    0.99
     imperson
    0.97
     forgotten
    0.96
     forgot
    0.95
     certainly
    0.93
     reconnect
    0.93
    Activations Density 0.316%

    No Known Activations