© 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. 7-RES-JB
    11. 6404
    Prev
    Next
    INDEX
    Explanations

    visual and technical representations such as illustrations, diagrams, and images with specific details or attributes

    oai_token-act-pair · gpt-3.5-turbo

    elements and components of visual representations or diagrams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asions
    -0.76
    iencies
    -0.72
    §
    -0.70
    entimes
    -0.69
    acious
    -0.69
    NULL
    -0.67
    bid
    -0.67
    aciously
    -0.67
    rit
    -0.66
    tests
    -0.65
    POSITIVE LOGITS
     diagram
    0.88
     underside
    0.87
     QR
    0.80
     typical
    0.74
    amorph
    0.74
     pict
    0.74
     prototype
    0.73
     Typical
    0.73
     enlarged
    0.73
     dimensions
    0.72
    Activations Density 0.281%

    No Known Activations