© 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. 31215
    Prev
    Next
    INDEX
    Explanations

    opening brackets or parentheses followed by the word "Bob"

    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
    0.7%
    223
    +0.12
    0.5%
    35
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.17
    0.08
    282
    +0.12
    0.09
    528
    +0.11
    0.06
    Negative Logits
    Environmental
    -0.67
    Reloaded
    -0.65
    ylum
    -0.64
    Common
    -0.62
    \">
    -0.61
     Cf
    -0.61
    Critical
    -0.60
     disturbing
    -0.60
     Nadu
    -0.59
    Rare
    -0.59
    POSITIVE LOGITS
    bie
    1.26
    bi
    1.08
    bies
    1.05
    bers
    1.00
    bles
    0.98
    cats
    0.97
    bing
    0.96
     Dylan
    0.94
    cat
    0.91
    bled
    0.90
    Activations Density 6.381%

    No Known Activations