© 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. 10-RES-JB
    11. 994
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to artistic elements such as writing style, violent content, set design, and musical motifs

    oai_token-act-pair · gpt-3.5-turbo

    elements of dark humor and impactful storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.87
    Register
    -0.83
    Desktop
    -0.82
    Republic
    -0.82
    Lago
    -0.80
     Preferred
    -0.80
    Registration
    -0.77
    LCS
    -0.77
    chuk
    -0.76
    MIT
    -0.75
    POSITIVE LOGITS
     visuals
    1.45
     humour
    1.44
     gore
    1.41
     suspense
    1.40
     humor
    1.39
     twists
    1.38
     narration
    1.37
     nudity
    1.37
     comedic
    1.34
     storytelling
    1.27
    Activations Density 0.504%

    No Known Activations