© 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. 3535
    Prev
    Next
    INDEX
    Explanations

    mentions of academic years in relation to athletes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to levels of education or experience in a sports context, particularly focusing on classifications like freshman, junior, and rookie

    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
    ichick
    -0.91
    ioned
    -0.82
    rosis
    -0.79
    anism
    -0.77
    raltar
    -0.73
    abulary
    -0.70
    roller
    -0.70
    ulhu
    -0.68
    argon
    -0.68
    efully
    -0.68
    POSITIVE LOGITS
     sensation
    0.94
     slump
    0.92
     QB
    0.83
     quarterback
    0.78
     catcher
    0.77
     batch
    0.75
     year
    0.74
    omore
    0.74
     phen
    0.72
     pitcher
    0.70
    Activations Density 0.056%

    No Known Activations