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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6914
    Prev
    Next
    INDEX
    Explanations

    image captions and photographer credits

    oai_token-act-pair · gpt-3.5-turbo

    image credit details and attributions

    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
     includ
    -0.69
     advis
    -0.69
    Advertisements
    -0.68
    """
    -0.67
    %:
    -0.67
     SHALL
    -0.66
     TAMADRA
    -0.66
    CONCLUS
    -0.65
    TABLE
    -0.65
    nil
    -0.63
    POSITIVE LOGITS
     Image
    0.95
     IMAGES
    0.77
     Courtesy
    0.74
     Ltd
    0.73
    ulton
    0.70
     Images
    0.66
    Courtesy
    0.62
     Photos
    0.62
     Circuit
    0.61
     Liberia
    0.61
    Activations Density 0.052%

    No Known Activations