© 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. 8-RES-JB
    11. 2505
    Prev
    Next
    INDEX
    Explanations

    image captions that include technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    prompts to enlarge content or toggle visibility options in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angers
    -0.63
    angering
    -0.63
    anger
    -0.63
     upt
    -0.62
     cardinal
    -0.60
    uality
    -0.60
    esses
    -0.60
     crowds
    -0.59
    fulness
    -0.58
    stood
    -0.58
    POSITIVE LOGITS
    ONSORED
    0.94
    Enlarge
    0.94
     WATCHED
    0.88
    UTERS
    0.81
     caption
    0.76
     toggle
    0.75
     "$:/
    0.75
     Image
    0.73
    hran
    0.72
     Flavoring
    0.71
    Activations Density 0.012%

    No Known Activations