© 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. 12022
    Prev
    Next
    INDEX
    Explanations

    phrases related to football strategies and player 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
    441
    +0.15
    0.5%
    314
    +0.14
    0.5%
    129
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.15
    0.04
    188
    +0.14
    0.03
    369
    +0.14
    0.03
    Negative Logits
    ashington
    -0.96
     Verb
    -0.92
    irlf
    -0.85
    livion
    -0.83
     Quinn
    -0.83
    Chat
    -0.81
    cci
    -0.81
     Typhoon
    -0.81
    catentry
    -0.80
    lynn
    -0.80
    POSITIVE LOGITS
    atoon
    1.01
    bolt
    0.93
    pole
    0.93
     doors
    0.89
    ocl
    0.87
     Poker
    0.82
     bounds
    0.81
    ailability
    0.81
    anded
    0.81
    asty
    0.81
    Activations Density 0.298%

    No Known Activations