© 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. 36639
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, specifically UFC fights and athletes

    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
    447
    +0.18
    0.9%
    288
    +0.12
    0.6%
    496
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.18
    0.06
    213
    +0.12
    0.04
    294
    +0.11
    0.02
    Negative Logits
    matter
    -0.80
    butt
    -0.69
     MacArthur
    -0.68
    izabeth
    -0.66
    gun
    -0.66
    ebted
    -0.66
     Pelosi
    -0.64
    capacity
    -0.64
    mary
    -0.64
    achi
    -0.64
    POSITIVE LOGITS
    PDATE
    0.84
     Fight
    0.82
    Fighting
    0.81
    UFC
    0.79
     Tonight
    0.77
     Tournament
    0.76
    PA
    0.74
    REAM
    0.73
     FIGHT
    0.70
     Network
    0.70
    Activations Density 8.146%

    No Known Activations