© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 2804
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports training camps

    oai_token-act-pair · gpt-3.5-turbo

    references to training camps and related sessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.79
    osi
    -0.76
    ionage
    -0.75
    eph
    -0.72
    hemy
    -0.72
    onyms
    -0.69
    xus
    -0.69
    writer
    -0.68
    metics
    -0.66
    agy
    -0.66
    POSITIVE LOGITS
     camp
    1.23
     regimen
    1.17
     camps
    1.12
     sessions
    1.11
     wheels
    1.03
    camp
    0.98
     session
    0.95
     facility
    0.95
     mont
    0.89
     exercises
    0.88
    Activations Density 0.049%

    No Known Activations