© 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. 11-RES-JB
    11. 4872
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'foul'

    oai_token-act-pair · gpt-3.5-turbo

    references to foul play in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.80
    PsyNetMessage
    -0.67
    iolet
    -0.64
    Ĭ±
    -0.62
    atism
    -0.61
    arians
    -0.61
     Rowling
    -0.60
    ocobo
    -0.60
    itals
    -0.59
    nown
    -0.58
    POSITIVE LOGITS
     smelling
    0.91
    weather
    0.87
    cery
    0.80
    sheet
    0.80
    mite
    0.79
    mouth
    0.79
    play
    0.77
    luent
    0.76
    ling
    0.74
     odor
    0.74
    Activations Density 0.066%

    No Known Activations