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. 20947
    Prev
    Next
    INDEX
    Explanations

    names of specific indigenous groups or regions, like "Kwakwaka'wakw"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific cultural group or community

    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
     Dresden
    -0.78
     UEFA
    -0.74
     rall
    -0.69
     inflamm
    -0.69
     ECB
    -0.68
     Constantine
    -0.67
     rpm
    -0.67
     SPD
    -0.67
     mathemat
    -0.66
    Generic
    -0.65
    POSITIVE LOGITS
    onga
    1.56
    ahi
    1.49
    wana
    1.47
    ui
    1.43
    anga
    1.41
    ua
    1.41
     Hawai
    1.40
    uku
    1.38
    wu
    1.36
    oba
    1.35
    Activations Density 0.250%

    No Known Activations