© 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. 11-RES-JB
    11. 21941
    Prev
    Next
    INDEX
    Explanations

    photographs or images

    oai_token-act-pair · gpt-3.5-turbo

    instances of photographs or images referenced in the text

    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
    ĪĴ
    -0.66
     leveling
    -0.63
    tons
    -0.58
     DirectX
    -0.58
    ŃĶ
    -0.57
     tang
    -0.57
     math
    -0.56
     calculus
    -0.56
    conom
    -0.56
     exerc
    -0.55
    POSITIVE LOGITS
     Photograph
    0.97
     Courtesy
    0.76
    ograph
    0.75
     courtesy
    0.75
    ribed
    0.74
     ©
    0.73
     copyright
    0.72
    archive
    0.71
    escription
    0.69
    orial
    0.68
    Activations Density 0.014%

    No Known Activations