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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 10313
    Prev
    Next
    INDEX
    Explanations

    This neuron looks for file names and possibly URL components

    oai_token-act-pair · gpt-3.5-turbo

    references to image file formats and their associated metadata

    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
    ndum
    -0.65
     numbering
    -0.63
     parentheses
    -0.62
     ¶
    -0.60
    ities
    -0.59
    âĢ¢âĢ¢
    -0.58
     ___
    -0.58
    tions
    -0.58
    ¶
    -0.57
     ¯
    -0.56
    POSITIVE LOGITS
    channelAvailability
    1.00
    quickShipAvailable
    0.99
    crop
    0.87
    ItemThumbnailImage
    0.86
    ãĥĻ
    0.79
    original
    0.75
    AAAAAAAA
    0.73
    Buyable
    0.73
    English
    0.71
    ROR
    0.70
    Activations Density 0.110%

    No Known Activations