© 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. 22451
    Prev
    Next
    INDEX
    Explanations

    words related to rule violations, particularly in sports or other competitive contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to fouls or rule violations

    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
    edia
    -0.84
    ocobo
    -0.76
    udeau
    -0.76
    itan
    -0.74
    _>
    -0.73
     Roosevelt
    -0.67
    igslist
    -0.67
    etsk
    -0.67
    aeda
    -0.66
    iro
    -0.66
    POSITIVE LOGITS
    cery
    1.01
     smelling
    0.88
    terness
    0.87
    sie
    0.82
     foul
    0.78
    mouth
    0.76
    s
    0.75
    rance
    0.68
     substances
    0.68
     misc
    0.67
    Activations Density 0.043%

    No Known Activations