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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15701
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals involved in specific incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    references to journalists or significant individuals involved in events

    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
    Characters
    -0.72
     VIDEOS
    -0.70
    Feel
    -0.69
    ctory
    -0.64
    Includes
    -0.63
    Shift
    -0.62
    Mods
    -0.61
    ":["
    -0.60
    cludes
    -0.59
    itiveness
    -0.59
    POSITIVE LOGITS
     murdered
    0.95
     tragically
    0.94
     allegedly
    0.92
     assassinated
    0.90
     gunned
    0.89
     notorious
    0.85
     fatally
    0.85
     alleged
    0.85
     famously
    0.84
     convicted
    0.84
    Activations Density 0.542%

    No Known Activations