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. 1-RES-JB
    6. 1441
    Prev
    Next
    INDEX
    Explanations

    references to the professional basketball player Steph Curry

    oai_token-act-pair · gpt-3.5-turbo

    references to Stephen Curry or related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.79
    innie
    -0.71
    graded
    -0.70
    evil
    -0.70
    sent
    -0.68
    ought
    -0.67
    ioch
    -0.66
     Gemini
    -0.65
    forced
    -0.64
    tered
    -0.63
    POSITIVE LOGITS
     Curry
    1.20
    oglu
    0.86
     Clicker
    0.86
    ModLoader
    0.83
    rer
    0.77
    erning
    0.76
     adolesc
    0.76
    rers
    0.74
     Cutter
    0.73
    sei
    0.73
    Activations Density 0.005%

    No Known Activations