© 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. 6-RES-JB
    11. 10975
    Prev
    Next
    INDEX
    Explanations

    functional commands and instructions involving clicking on buttons

    oai_token-act-pair · gpt-3.5-turbo

    instructions or prompts related to clicking links or buttons, particularly in a digital interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redes
    -0.74
    obic
    -0.73
    ngth
    -0.72
    ensical
    -0.70
    angering
    -0.69
    udeb
    -0.67
    lycer
    -0.64
    luster
    -0.62
     vou
    -0.61
     afloat
    -0.61
    POSITIVE LOGITS
     button
    1.16
     buttons
    0.87
     Refresh
    0.80
     icon
    0.76
     slider
    0.75
    button
    0.74
     arrow
    0.74
     arrows
    0.73
     shutter
    0.73
     accelerator
    0.72
    Activations Density 0.090%

    No Known Activations