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. 5-RES-JB
    6. 6935
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Robin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Robin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.87
    ormons
    -0.75
    xual
    -0.75
    gerald
    -0.74
    resso
    -0.72
    aeda
    -0.69
     haste
    -0.69
    gregation
    -0.69
    ormon
    -0.68
    chnology
    -0.68
    POSITIVE LOGITS
     Hood
    1.25
    ette
    0.92
    alties
    0.85
     Williams
    0.83
     Rout
    0.78
     Robin
    0.75
     Hob
    0.75
     Bean
    0.75
    otte
    0.73
     Hanson
    0.73
    Activations Density 0.016%

    No Known Activations