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

    Neuronpedia

    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. 6-RES-JB
    11. 10761
    Prev
    Next
    INDEX
    Explanations

    images or photographs in a document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of images and photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osi
    -0.78
     congress
    -0.69
    bilt
    -0.64
     theorem
    -0.60
    SSL
    -0.59
    vernment
    -0.59
    merce
    -0.58
     nonviolent
    -0.58
     Stra
    -0.57
    soType
    -0.57
    POSITIVE LOGITS
    ynthesis
    1.49
    ensitive
    1.32
    ynt
    1.21
     depicting
    1.07
    mith
    1.01
    ensitivity
    1.00
    creen
    1.00
    ystem
    0.95
    hots
    0.94
    paces
    0.93
    Activations Density 0.059%

    No Known Activations