© 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. 7798
    Prev
    Next
    INDEX
    Explanations

    terms related to sports positions and team strategies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports team roster management and player acquisition

    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
     humour
    -0.73
    romy
    -0.71
     concess
    -0.70
     Feminist
    -0.69
     Poverty
    -0.67
     mu
    -0.66
    eva
    -0.65
    ische
    -0.65
     cens
    -0.65
    ITNESS
    -0.65
    POSITIVE LOGITS
     offensively
    1.48
     defensively
    1.26
     offseason
    1.21
     athlet
    1.18
     quarterback
    1.05
     Playoff
    1.04
    Coach
    1.03
     coaching
    1.00
     cornerback
    0.99
     Coach
    0.98
    Activations Density 0.412%

    No Known Activations