© 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. 36085
    Prev
    Next
    INDEX
    Explanations

    information related to baseball players, especially pitchers, their injuries, and statistics such as ERA and innings pitched

    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
    0.9%
    575
    +0.11
    0.7%
    617
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.15
    0.07
    326
    +0.11
    0.17
    718
    +0.08
    0.10
    Negative Logits
    illion
    -0.57
     Lumpur
    -0.56
    ees
    -0.56
     Dhabi
    -0.54
    uries
    -0.54
    zhou
    -0.52
    ives
    -0.51
    Guard
    -0.51
    isec
    -0.51
    icle
    -0.50
    POSITIVE LOGITS
     pitcher
    0.77
     pitchers
    0.69
     pitching
    0.61
     pitched
    0.57
     coach
    0.56
     ERA
    0.55
     mound
    0.53
     reliever
    0.53
     catcher
    0.52
     hur
    0.52
    Activations Density 5.525%

    No Known Activations