© 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. 31230
    Prev
    Next
    INDEX
    Explanations

    information related to Manchester City

    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
    +0.31
    1.4%
    241
    +0.13
    0.6%
    269
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.31
    0.07
    656
    +0.13
    0.10
    732
    +0.11
    0.06
    Negative Logits
    ãĥ´
    -0.89
    Els
    -0.82
     Ples
    -0.81
     Zup
    -0.79
    ãĥł
    -0.79
     Macy
    -0.78
    clus
    -0.72
    natureconservancy
    -0.71
    TED
    -0.70
    pee
    -0.70
    POSITIVE LOGITS
     Hots
    1.11
     FC
    0.92
     Football
    0.91
     midfielder
    0.90
     sacked
    0.86
    wich
    0.85
     footballer
    0.83
     organising
    0.83
     goalkeeper
    0.83
     Munich
    0.82
    Activations Density 13.122%

    No Known Activations