© 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. 6795
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or user interaction

    oai_token-act-pair · gpt-3.5-turbo

    clicks or interactions related to navigation and actions on a website

    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
    ynthesis
    -0.66
    BuyableInstoreAndOnline
    -0.65
    udeb
    -0.62
    Winter
    -0.62
    giving
    -0.60
    APD
    -0.59
    awi
    -0.58
    Fel
    -0.58
    obic
    -0.58
     minds
    -0.57
    POSITIVE LOGITS
     button
    1.13
    button
    1.03
     icon
    1.01
     buttons
    0.92
     arrow
    0.89
     [+]
    0.84
     banner
    0.84
     arrows
    0.84
     icons
    0.79
    actions
    0.77
    Activations Density 0.055%

    No Known Activations