© 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. 1-RES-JB
    11. 16857
    Prev
    Next
    INDEX
    Explanations

    locations, specifically focusing on places and institutions like Redmond, Bellevue, and Stamford

    oai_token-act-pair · gpt-3.5-turbo

    place names and notable locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuel
    -0.83
    selection
    -0.80
    hift
    -0.71
    ESH
    -0.71
    har
    -0.70
    actionDate
    -0.70
    actor
    -0.70
     Volunte
    -0.69
    fact
    -0.68
     Annotations
    -0.67
    POSITIVE LOGITS
     mosqu
    0.94
     Redmond
    0.89
    alties
    0.87
    yip
    0.86
     nodd
    0.79
    monds
    0.74
    uckland
    0.73
    pora
    0.73
    wig
    0.73
     Dempsey
    0.72
    Activations Density 0.023%

    No Known Activations