© 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. 21370
    Prev
    Next
    INDEX
    Explanations

    Click actions or buttons in online interfaces

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to clicking links or buttons

    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
    ynthesis
    -0.73
    udeb
    -0.68
    anmar
    -0.67
    aturdays
    -0.64
    ovember
    -0.63
    giving
    -0.62
    lycer
    -0.61
    lance
    -0.60
    Week
    -0.59
    UCT
    -0.59
    POSITIVE LOGITS
     button
    1.14
     buttons
    0.97
     icon
    0.90
     arrow
    0.82
     arrows
    0.81
    ĵĺ
    0.80
    button
    0.78
     Refresh
    0.77
     [+]
    0.76
     Icon
    0.75
    Activations Density 0.061%

    No Known Activations