© 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. 11-RES-JB
    11. 24500
    Prev
    Next
    INDEX
    Explanations

    specific numerical data, especially related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    information related to healthcare facilities and regulations

    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
    soType
    -0.82
    ItemThumbnailImage
    -0.73
    fml
    -0.72
    attribute
    -0.72
    DragonMagazine
    -0.70
     secondly
    -0.69
    vir
    -0.68
    SPONSORED
    -0.68
    Appearance
    -0.68
     afterwards
    -0.68
    POSITIVE LOGITS
     dozens
    0.91
     nine
    0.89
     seven
    0.88
     Durham
    0.87
     Chattanooga
    0.87
     Anchorage
    0.87
     Syracuse
    0.87
     Albuquerque
    0.86
     Oakland
    0.85
     Asheville
    0.85
    Activations Density 0.567%

    No Known Activations