© 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. 15179
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "canon" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Canon," whether in the context of film, scripture, or any specific canon of works

    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
    warts
    -0.82
    orns
    -0.73
    pants
    -0.67
    oran
    -0.66
     Skies
    -0.64
    ":[
    -0.63
    opping
    -0.63
    Reviewer
    -0.63
    oft
    -0.62
    scape
    -0.61
    POSITIVE LOGITS
    ical
    0.95
    ITED
    0.91
    edient
    0.85
    ciating
    0.84
    ulously
    0.83
    heit
    0.82
    ital
    0.80
    itable
    0.79
    icable
    0.78
    sembly
    0.77
    Activations Density 0.133%

    No Known Activations