© 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. 32211
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports plays and performances, particularly in football and baseball

    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
    0.8%
    603
    +0.12
    0.5%
    668
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.18
    -0.09
    195
    +0.12
    -0.00
    566
    +0.12
    0.15
    Negative Logits
     redacted
    -0.79
     transcripts
    -0.70
     Transcript
    -0.69
    orno
    -0.69
     Authorization
    -0.68
    nih
    -0.67
    anamo
    -0.65
     persons
    -0.64
     withholding
    -0.64
     memos
    -0.64
    POSITIVE LOGITS
     tremend
    0.93
    ĸļ
    0.93
     clutch
    0.92
     spectacular
    0.90
     stride
    0.88
     impress
    0.87
     brilliantly
    0.87
     Jagu
    0.87
     impressive
    0.86
    GGGGGGGG
    0.83
    Activations Density 18.753%

    No Known Activations