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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 1795
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance, especially goals, points, assists, tackles, sacks, and hits

    oai_token-act-pair · gpt-3.5-turbo

    statistical performance metrics related to sports achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yg
    -0.75
    uncture
    -0.69
     Exam
    -0.67
    hod
    -0.65
    abus
    -0.64
     Hath
    -0.64
    sonian
    -0.63
    aucas
    -0.61
    OOL
    -0.59
    gra
    -0.59
    POSITIVE LOGITS
     apiece
    1.36
     batted
    0.98
     scored
    0.85
     plus
    0.84
     conceded
    0.83
     overall
    0.82
     totaling
    0.81
     per
    0.80
     shy
    0.78
     accrued
    0.77
    Activations Density 0.079%

    No Known Activations