© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35389
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, particularly those involving competitions and matchups

    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
    •Layer 6 UMAP region: Mixed cluster on right - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    608
    +0.07
    0.5%
    83
    +0.07
    0.5%
    587
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.07
    0.23
    362
    +0.07
    0.18
    393
    +0.06
    0.26
    Negative Logits
    hoe
    -0.50
    plugins
    -0.48
    Ohio
    -0.47
    lees
    -0.47
    Aust
    -0.46
    igent
    -0.46
    flows
    -0.46
    reements
    -0.45
    bench
    -0.44
    bt
    -0.44
    POSITIVE LOGITS
     redemption
    0.60
     immortality
    0.57
     fame
    0.52
     sneak
    0.51
     reproduce
    0.51
     rebirth
    0.50
     conception
    0.48
     citizenship
    0.46
     rejuven
    0.46
     revenge
    0.45
    Activations Density 8.618%

    No Known Activations