© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12192
    Prev
    Next
    INDEX
    Explanations

    information about people's involvement in sports, including coaching, playing, and management positions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    185
    +0.10
    0.4%
    647
    +0.10
    0.4%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.10
    0.08
    668
    +0.10
    0.06
    603
    +0.10
    0.07
    Negative Logits
    thur
    -0.83
    ophe
    -0.83
    plan
    -0.82
    react
    -0.77
     hypotheses
    -0.72
    rants
    -0.71
     weeds
    -0.71
    opers
    -0.70
    opath
    -0.70
     correctness
    -0.70
    POSITIVE LOGITS
     unsuccessfully
    1.00
     briefly
    0.99
    monton
    0.95
    iscons
    0.87
     stint
    0.85
     extensively
    0.84
     famously
    0.81
    ookie
    0.81
    Ô
    0.81
    è£ħ
    0.80
    Activations Density 2.272%

    No Known Activations