© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 11409
    Prev
    Next
    INDEX
    Explanations

    sports-related information and player analysis

    oai_token-act-pair · gpt-3.5-turbo

    discussions about potential and analysis in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrics
    -0.81
     laun
    -0.67
     apologise
    -0.67
     humour
    -0.65
    "},{"
    -0.64
    anguage
    -0.63
    estic
    -0.63
    liament
    -0.62
    verend
    -0.62
     lyrics
    -0.61
    POSITIVE LOGITS
     versatility
    0.94
     matchup
    0.91
     rookie
    0.88
     cornerback
    0.84
    ivably
    0.84
     underrated
    0.84
     handc
    0.84
     offseason
    0.83
     positional
    0.83
     linebackers
    0.82
    Activations Density 0.556%

    No Known Activations