© 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. 17102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "picture" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "picture" and its variants, indicating a focus on visual representations 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
    iencies
    -0.80
    iott
    -0.79
    steen
    -0.74
    iance
    -0.73
    iant
    -0.72
    onite
    -0.72
    orne
    -0.71
    bard
    -0.71
    indal
    -0.69
    ishops
    -0.69
    POSITIVE LOGITS
    que
    1.02
    picture
    0.98
     gallery
    0.90
     galleries
    0.88
    journal
    0.88
     depicting
    0.86
    clip
    0.85
     img
    0.84
     illustration
    0.78
    Pixel
    0.78
    Activations Density 0.036%

    No Known Activations