© 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. 2731
    Prev
    Next
    INDEX
    Explanations

    images and references to pictures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of photographs or images

    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
    osi
    -0.71
     streng
    -0.67
     congress
    -0.64
     Rutherford
    -0.62
     theorem
    -0.61
    upuncture
    -0.59
    inion
    -0.58
     bund
    -0.58
     footing
    -0.58
     manslaughter
    -0.57
    POSITIVE LOGITS
    ynthesis
    1.50
    ensitive
    1.33
    ynt
    1.27
    creen
    1.06
     depicting
    1.05
    ensitivity
    1.01
    que
    0.95
    hots
    0.95
    amples
    0.94
     photos
    0.92
    Activations Density 0.071%

    No Known Activations