© 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. 31103
    Prev
    Next
    INDEX
    Explanations

    keywords related to fire, flames, and potentially dangerous situations

    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
    +0.17
    0.6%
    755
    +0.16
    0.6%
    167
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.17
    0.09
    167
    +0.16
    -0.01
    99
    +0.16
    0.08
    Negative Logits
    ĸļ
    -1.00
    xus
    -0.98
     Morg
    -0.96
    berra
    -0.91
     Lans
    -0.89
    edy
    -0.87
    eter
    -0.84
    DonaldTrump
    -0.84
    eday
    -0.84
    atem
    -0.83
    POSITIVE LOGITS
    flies
    1.60
    storm
    1.35
    fly
    1.29
    balls
    1.28
    proof
    1.25
    fighter
    1.23
    storms
    1.20
     exting
    1.15
    bats
    1.15
    birds
    1.12
    Activations Density 6.439%

    No Known Activations