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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 9347
    Prev
    Next
    INDEX
    Explanations

    mentions of various names, possibly of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of well-known chefs and culinary figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FANTASY
    -0.59
     VERS
    -0.58
     Manip
    -0.56
     greatness
    -0.55
     Rebirth
    -0.54
     cryptocurrency
    -0.53
     seriously
    -0.53
     headquarters
    -0.52
    ENTION
    -0.51
     Newsletter
    -0.51
    POSITIVE LOGITS
    inski
    1.06
    anski
    1.05
    kson
    1.03
    icz
    1.02
    iani
    0.98
    zinski
    0.98
    quist
    0.97
    ucci
    0.97
    owski
    0.96
    onson
    0.95
    Activations Density 0.353%

    No Known Activations