Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8670
    Prev
    Next
    INDEX
    Explanations

    terms related to technological interfaces

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of "interfaces."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mills
    -0.78
     Torn
    -0.78
    raised
    -0.72
    lesiastical
    -0.71
    ŀ
    -0.70
    yss
    -0.69
     Kelley
    -0.69
    vere
    -0.68
    mort
    -0.68
     SOLD
    -0.67
    POSITIVE LOGITS
     interface
    3.65
     interfaces
    2.98
     Interface
    2.82
    interface
    2.69
    Interface
    2.16
     GUI
    1.52
     UI
    1.48
    GUI
    1.36
     interf
    1.29
     API
    1.27
    Activations Density 0.013%

    No Known Activations