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. 2-RES-JB
    6. 20369
    Prev
    Next
    INDEX
    Explanations

    names or mentions related to the name 'Su'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Su" followed by various contexts or associations, likely relating to individuals or entities identified with that prefix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.74
     Fiber
    -0.72
     directions
    -0.71
    wright
    -0.68
    hyde
    -0.68
    ãĤ¡
    -0.68
    naires
    -0.67
    lehem
    -0.66
     juggling
    -0.65
     Orbit
    -0.62
    POSITIVE LOGITS
    pper
    1.13
    arez
    1.12
    icidal
    1.10
    icides
    1.09
    zanne
    1.01
    ples
    0.98
    icide
    0.95
    pped
    0.95
    idan
    0.93
    pling
    0.92
    Activations Density 0.007%

    No Known Activations