© 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. 20570
    Prev
    Next
    INDEX
    Explanations

    news sources and photographers' credits in captions

    oai_token-act-pair · gpt-3.5-turbo

    references to photo credit and media sources

    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
    \":
    -0.73
    76561
    -0.67
    cible
    -0.62
    ="#
    -0.60
    ',"
    -0.59
    iott
    -0.59
     favour
    -0.58
     revol
    -0.56
    ':
    -0.55
     reven
    -0.55
    POSITIVE LOGITS
     Images
    0.90
    Images
    0.60
    ebra
    0.58
    Vari
    0.58
    ached
    0.57
    File
    0.57
     Buy
    0.57
    umi
    0.57
    )
    0.56
     IMAGES
    0.56
    Activations Density 0.040%

    No Known Activations