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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45868
    Prev
    Next
    INDEX
    Explanations

    references to professional wrestling events and personalities, particularly from WWE

    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
    +0.15
    0.7%
    288
    +0.12
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.15
    0.21
    138
    +0.12
    0.19
    64
    +0.10
    -0.21
    Negative Logits
    emort
    -0.89
    uries
    -0.88
    ouver
    -0.83
    elong
    -0.83
    yrinth
    -0.82
    ĺħ
    -0.80
    milo
    -0.79
    anwhile
    -0.77
    perse
    -0.77
    abet
    -0.76
    POSITIVE LOGITS
    Mania
    1.08
    restling
    1.08
     NXT
    1.06
     Wrestle
    1.03
     Universe
    0.99
     McMahon
    0.95
     Championship
    0.88
     RAW
    0.85
     WWE
    0.85
     wrestlers
    0.84
    Activations Density 10.164%

    No Known Activations