© 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. 10-RES-JB
    11. 12357
    Prev
    Next
    INDEX
    Explanations

    technical terms related to image processing

    oai_token-act-pair · gpt-3.5-turbo

    elements related to structured processes or steps, particularly in the context of visual content or imagery

    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
     Dent
    -0.89
     Cooper
    -0.86
     bourbon
    -0.85
     Trem
    -0.85
     Donn
    -0.84
     Tend
    -0.83
     Brist
    -0.82
     Dru
    -0.82
     Burr
    -0.82
    Tenn
    -0.80
    POSITIVE LOGITS
     Images
    1.33
    image
    1.28
     Image
    1.25
     image
    1.23
    Image
    1.21
    Images
    1.20
     images
    1.18
    images
    1.13
    img
    0.95
     IMAGES
    0.90
    Activations Density 0.356%

    No Known Activations