© 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. 0-RES-JB
    11. 11543
    Prev
    Next
    INDEX
    Explanations

    official website domains

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Site" or related site references, indicating an emphasis on official webpages or locations

    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
     quart
    -0.69
     rolls
    -0.68
     card
    -0.68
     rabb
    -0.66
     pudding
    -0.65
     kings
    -0.65
     fortune
    -0.64
     shine
    -0.64
     cards
    -0.63
    pressed
    -0.62
    POSITIVE LOGITS
     Site
    3.52
    Site
    2.38
     Sites
    1.92
     Species
    1.57
     Facility
    1.38
     Ship
    1.01
     Facilities
    1.00
     Zone
    1.00
     Buildings
    0.94
     Installation
    0.93
    Activations Density 0.018%

    No Known Activations