© 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. 31113
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition, conflict, and comparison in text data, especially focusing on contentious or conflicting topics

    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
    +0.30
    1.5%
    481
    +0.10
    0.5%
    669
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.30
    0.14
    616
    +0.10
    0.12
    251
    +0.10
    0.11
    Negative Logits
     Canaver
    -0.66
     Sturgeon
    -0.64
     tyr
    -0.59
     Monsters
    -0.59
    ĸļ
    -0.58
     Rampage
    -0.58
     Statue
    -0.57
    HAEL
    -0.56
     Kamp
    -0.56
    awaru
    -0.55
    POSITIVE LOGITS
    âĢij
    0.82
    -
    0.82
    hand
    0.80
    âĢIJ
    0.77
    outs
    0.77
    landers
    0.77
    hang
    0.74
    lining
    0.71
    cast
    0.70
    sell
    0.68
    Activations Density 21.725%

    No Known Activations