© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20036
    Prev
    Next
    INDEX
    Explanations

    mentions of sports leagues and professional events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to professional sports and their associated media coverage

    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
    yip
    -0.75
     pend
    -0.70
     tune
    -0.65
    amsung
    -0.64
    #$
    -0.62
     swelling
    -0.62
     UNESCO
    -0.61
    gio
    -0.60
     ib
    -0.59
     toget
    -0.58
    POSITIVE LOGITS
    mbudsman
    0.84
    Wallet
    0.83
    tracks
    0.77
     Responsibility
    0.75
     Claims
    0.75
    Events
    0.74
    Fest
    0.73
    arel
    0.72
     Values
    0.72
     Edition
    0.70
    Activations Density 0.349%

    No Known Activations