© 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. 5081
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface design, particularly focusing on UI components and features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of user interface (UI) and user experience (UX) elements

    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
    女
    -0.84
    wagen
    -0.77
    inosaur
    -0.77
    ership
    -0.74
    aunder
    -0.67
    esson
    -0.66
     Gutenberg
    -0.66
    ival
    -0.66
    nir
    -0.66
    itude
    -0.66
    POSITIVE LOGITS
    UI
    0.98
    PDATE
    0.91
    FW
    0.84
    BG
    0.82
     clipboard
    0.77
    Kit
    0.77
     UI
    0.76
    TAG
    0.75
     practition
    0.75
     hoops
    0.74
    Activations Density 0.007%

    No Known Activations