© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 16101
    Prev
    Next
    INDEX
    Explanations

    years related to sports seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports seasons or statistical rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clever
    -0.68
     scrut
    -0.65
     horizont
    -0.63
    pload
    -0.61
     Juda
    -0.61
     Bones
    -0.59
    Anderson
    -0.59
    udos
    -0.58
     Stones
    -0.58
    Joy
    -0.58
    POSITIVE LOGITS
     season
    0.86
     editions
    0.84
     timeframe
    0.79
     seasons
    0.79
     attRot
    0.75
     edition
    0.75
     onwards
    0.74
    iphate
    0.73
     Outlook
    0.70
     Season
    0.69
    Activations Density 0.046%

    No Known Activations