© 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. 7-RES-JB
    11. 23754
    Prev
    Next
    INDEX
    Explanations

    information related to sports and athletics, specifically player characteristics and recruitment details

    oai_token-act-pair · gpt-3.5-turbo

    numerical descriptions and statistics related to athlete performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologise
    -0.81
     Capitalism
    -0.78
     realise
    -0.78
     Paradox
    -0.78
     recognise
    -0.74
     msec
    -0.73
     Shank
    -0.72
     Orchestra
    -0.71
     apologised
    -0.69
     civilisation
    -0.68
    POSITIVE LOGITS
     undrafted
    1.40
     freshman
    1.04
     scouts
    1.03
     sophomore
    1.02
    UF
    1.01
     athlet
    1.00
    College
    1.00
     workouts
    1.00
     collegiate
    0.99
     athleticism
    0.98
    Activations Density 0.689%

    No Known Activations