© 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. 0-RES-JB
    11. 8414
    Prev
    Next
    INDEX
    Explanations

    themes within various contexts, such as literature, music, and movies

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring themes in various contexts

    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
    effective
    -0.72
    carry
    -0.67
    nder
    -0.64
     downed
    -0.64
    undo
    -0.64
     bow
    -0.63
    bil
    -0.63
    raction
    -0.62
    mit
    -0.61
    tesy
    -0.61
    POSITIVE LOGITS
     themes
    3.89
     theme
    2.64
     Theme
    1.99
    theme
    1.95
    Theme
    1.94
     motif
    1.91
     tropes
    1.71
     topics
    1.70
     themed
    1.44
     storylines
    1.43
    Activations Density 0.017%

    No Known Activations