© 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. 18613
    Prev
    Next
    INDEX
    Explanations

    terms related to published materials like scripts, storyboards, and books

    oai_token-act-pair · gpt-3.5-turbo

    mentions of film-related content and supplementary materials

    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
    force
    -0.82
    amphetamine
    -0.80
    FML
    -0.78
    Factor
    -0.76
    Initialized
    -0.75
    Ĥİ
    -0.75
    Merit
    -0.74
    forces
    -0.73
    severe
    -0.73
    ooters
    -0.72
    POSITIVE LOGITS
     interviews
    1.49
     photographs
    1.37
     annotations
    1.36
     excerpts
    1.35
     essays
    1.35
     illustrations
    1.31
     quotations
    1.30
     transcripts
    1.30
     commentary
    1.27
     sketches
    1.27
    Activations Density 0.363%

    No Known Activations