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. 11-RES-JB
    6. 20137
    Prev
    Next
    INDEX
    Explanations

    comparisons and relationships between different entities or things

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases related to standards and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.79
    odder
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
    ertodd
    -0.76
    ovie
    -0.75
    paio
    -0.74
    adow
    -0.74
    inventoryQuantity
    -0.73
    utenberg
    -0.73
    ĪĴ
    -0.73
    POSITIVE LOGITS
     foreigner
    1.86
     foreigners
    1.85
     overseas
    1.79
     Europeans
    1.76
     abroad
    1.74
     foreign
    1.61
     Indones
    1.57
     Taiwanese
    1.56
     countries
    1.56
    foreign
    1.52
    Activations Density 1.275%

    No Known Activations