© 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. 31274
    Prev
    Next
    INDEX
    Explanations

    sports teams or related terms

    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
    +0.08
    0.5%
    146
    +0.07
    0.5%
    292
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.08
    0.02
    26
    +0.07
    0.12
    221
    +0.06
    0.04
    Negative Logits
     Carmen
    -0.46
     challeng
    -0.44
    igation
    -0.44
    NetMessage
    -0.44
    heim
    -0.43
     Dru
    -0.43
     colleg
    -0.42
    nings
    -0.42
     è£ıè¦ļéĨĴ
    -0.42
     WRITE
    -0.41
    POSITIVE LOGITS
    arters
    0.54
    riad
    0.52
    arter
    0.51
    inches
    0.51
    alion
    0.49
    olds
    0.48
    ombo
    0.48
    uesday
    0.46
    ruits
    0.46
    urrencies
    0.46
    Activations Density 19.450%

    No Known Activations