© 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. 10-RES-JB
    11. 11455
    Prev
    Next
    INDEX
    Explanations

    references to photo captions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of photographs and visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ministic
    -0.76
    merce
    -0.74
    hattan
    -0.67
    mington
    -0.62
    stood
    -0.62
     foreseeable
    -0.61
    ancial
    -0.61
     Hutchinson
    -0.60
     blot
    -0.60
    sembly
    -0.57
    POSITIVE LOGITS
     Caption
    0.84
    Gallery
    0.73
     Photos
    0.72
    ource
    0.71
    Photos
    0.67
    ets
    0.65
    ynthesis
    0.65
    ensitive
    0.64
    س
    0.63
     Amount
    0.62
    Activations Density 0.010%

    No Known Activations