© 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. 45680
    Prev
    Next
    INDEX
    Explanations

    the word "exact" when it appears with numerical values across various texts

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    7
    +0.16
    0.6%
    362
    +0.14
    0.5%
    651
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.18
    124
    +0.14
    0.13
    167
    +0.14
    -0.01
    Negative Logits
    rift
    -0.89
    ker
    -0.87
    ipolar
    -0.82
     ashore
    -0.81
    ulton
    -0.80
    ublic
    -0.79
    NetMessage
    -0.77
     Pigs
    -0.76
    stown
    -0.75
    HS
    -0.75
    POSITIVE LOGITS
    itude
    1.07
     opposite
    0.99
     wording
    0.99
     embodiment
    0.97
    ions
    0.95
     same
    0.94
    aneous
    0.94
     amount
    0.92
    ing
    0.92
     exact
    0.92
    Activations Density 7.585%

    No Known Activations