© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20762
    Prev
    Next
    INDEX
    Explanations

    words related to pranks and circus-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to pranks and circus-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ibid
    -0.80
    arian
    -0.78
    jamin
    -0.77
    ishop
    -0.76
    arians
    -0.76
    obal
    -0.73
    Dialogue
    -0.72
    oice
    -0.72
    xual
    -0.71
    ahead
    -0.71
    POSITIVE LOGITS
    bus
    0.88
     prank
    0.84
     Mouse
    0.83
     juggling
    0.80
    STER
    0.78
     amuse
    0.76
    tail
    0.76
    ster
    0.73
     err
    0.70
     Circus
    0.70
    Activations Density 0.065%

    No Known Activations