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. 8478
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    country names and their variations

    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
     Intelligent
    -0.68
     Loft
    -0.67
     McH
    -0.66
     Architects
    -0.64
     Horowitz
    -0.63
    Miller
    -0.62
     clerks
    -0.60
     Sons
    -0.60
     HAL
    -0.60
     aph
    -0.60
    POSITIVE LOGITS
    uania
    1.42
    istan
    1.30
    nesia
    1.23
    agascar
    1.18
     Yugoslavia
    1.18
    ussia
    1.16
    itzerland
    1.16
     Rica
    1.16
    inia
    1.16
    ailand
    1.15
    Activations Density 0.218%

    No Known Activations