Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20692
    Prev
    Next
    INDEX
    Explanations

    mentions of famous literary figures, particularly Shakespeare

    oai_token-act-pair · gpt-3.5-turbo

    mentions of literary figures, particularly Shakespeare and other classic writers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MIN
    -0.71
    Gear
    -0.68
     gran
    -0.68
     controllers
    -0.67
    KT
    -0.67
     DK
    -0.66
    avor
    -0.66
     alerted
    -0.64
    ensed
    -0.64
     sd
    -0.62
    POSITIVE LOGITS
     Shakespeare
    3.88
    akespeare
    2.32
     Nietzsche
    1.85
     Dickens
    1.83
     Tolkien
    1.68
    akespe
    1.65
     Lovecraft
    1.61
     Twain
    1.38
     Hitchcock
    1.34
     Romeo
    1.33
    Activations Density 0.026%

    No Known Activations