© 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. 7512
    Prev
    Next
    INDEX
    Explanations

    numerical values followed by a plus sign indicating a positive relationship or addition

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, specifically those indicating quantities or scores

    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
    rog
    -0.78
    lon
    -0.77
    venge
    -0.75
    son
    -0.75
    idine
    -0.73
    rius
    -0.71
    coat
    -0.70
    ©¶æ
    -0.70
    bear
    -0.68
    xton
    -0.68
    POSITIVE LOGITS
     pages
    0.95
     IMAGES
    0.94
     hours
    0.91
     degrees
    0.87
     mph
    0.86
     intersections
    0.86
     years
    0.85
     acres
    0.82
     minutes
    0.80
     MPH
    0.79
    Activations Density 0.042%

    No Known Activations