© 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. 3-RES-JB
    11. 14786
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "image."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "image" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endez
    -0.91
    ighter
    -0.90
    ighters
    -0.86
    aptic
    -0.83
    merce
    -0.82
    laws
    -0.80
    iday
    -0.79
    cffff
    -0.79
    hurst
    -0.78
    uum
    -0.78
    POSITIVE LOGITS
     image
    0.99
     caption
    0.96
     gallery
    0.88
     photographed
    0.83
    gallery
    0.82
     macros
    0.81
     galleries
    0.80
     images
    0.80
     thumbnail
    0.80
     mosaic
    0.78
    Activations Density 0.019%

    No Known Activations