© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2934
    Prev
    Next
    INDEX
    Explanations

    references to physical locations, specifically headquarters

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational headquarters

    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
    kees
    -0.67
    hemy
    -0.65
    ury
    -0.64
     "$:/
    -0.63
    pun
    -0.63
    iven
    -0.63
     [/
    -0.62
    ick
    -0.62
    essing
    -0.61
    unn
    -0.61
    POSITIVE LOGITS
     headquarters
    3.69
     Headquarters
    2.88
     HQ
    2.48
     offices
    2.04
     headquartered
    1.46
    HQ
    1.27
     office
    1.27
     warehouses
    1.21
     barracks
    1.17
     lair
    1.17
    Activations Density 0.011%

    No Known Activations