© 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. 11-RES-JB
    11. 15738
    Prev
    Next
    INDEX
    Explanations

    captions related to image enlargement toggles

    oai_token-act-pair · gpt-3.5-turbo

    commands or functions related to images and captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atever
    -0.65
    dies
    -0.62
    bats
    -0.61
    senal
    -0.59
    naires
    -0.57
    doms
    -0.56
    speak
    -0.55
     toget
    -0.55
    ablishment
    -0.54
    ournal
    -0.53
    POSITIVE LOGITS
     caption
    1.26
     toggle
    0.85
    taboola
    0.77
    %]
    0.71
    ption
    0.70
     copyright
    0.68
     Courtesy
    0.65
     Image
    0.62
     url
    0.59
    Chart
    0.59
    Activations Density 0.006%

    No Known Activations