© 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. 4-RES-JB
    11. 7849
    Prev
    Next
    INDEX
    Explanations

    words related to scrolling

    oai_token-act-pair · gpt-3.5-turbo

    references to scrolling actions in digital content

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

    No Comments

    Negative Logits
    stood
    -0.85
    noxious
    -0.71
    ften
    -0.68
    ilities
    -0.66
    ¢
    -0.65
    responsible
    -0.65
    jured
    -0.64
     household
    -0.64
    jury
    -0.64
    Sov
    -0.63
    POSITIVE LOGITS
     scroll
    1.01
     scrolls
    1.00
     scrolling
    0.97
     Scroll
    0.97
    scroll
    0.93
    antry
    0.86
    efully
    0.79
    wheel
    0.78
    itzer
    0.78
    chemy
    0.77
    Activations Density 0.008%

    No Known Activations