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. 10602
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity named "Whyalla"

    oai_token-act-pair · gpt-3.5-turbo

    the name "alla" as well as certain location and organizational identifiers

    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
     IPM
    -0.96
     Traff
    -0.68
     Fuji
    -0.68
    Hay
    -0.67
     PowerPoint
    -0.67
     sweats
    -0.65
     Hib
    -0.65
     cracks
    -0.65
    mpeg
    -0.64
     FTA
    -0.64
    POSITIVE LOGITS
    alla
    2.92
    ë
    2.50
    LD
    1.35
    allas
    1.30
     Lok
    1.27
     destiny
    1.18
    arde
    0.98
    alli
    0.91
    halla
    0.90
     earners
    0.86
    Activations Density 0.038%

    No Known Activations