© 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. 36958
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    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
    393
    +0.20
    1.0%
    447
    +0.14
    0.7%
    674
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.30
    608
    +0.14
    0.21
    375
    +0.12
    0.08
    Negative Logits
    rats
    -0.84
    ħĭ
    -0.80
    rat
    -0.79
    oons
    -0.78
    brates
    -0.73
    ORTS
    -0.73
    rates
    -0.72
    acus
    -0.71
    ETS
    -0.67
    atu
    -0.67
    POSITIVE LOGITS
     luck
    0.96
     extra
    0.84
     fun
    0.80
     flair
    0.75
    icial
    0.73
     caution
    0.72
     overlap
    0.71
     realism
    0.71
    angu
    0.69
     consolation
    0.69
    Activations Density 11.433%

    No Known Activations