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. 11935
    Prev
    Next
    INDEX
    Explanations

    geographical locations, particularly regions, cities, towns, and provinces

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and regions

    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
     bandwagon
    -0.64
    Factor
    -0.63
    oulos
    -0.60
    Lear
    -0.60
    xon
    -0.60
    wcsstore
    -0.59
     Dollars
    -0.59
    ctive
    -0.58
    thumbnails
    -0.58
     Robo
    -0.57
    POSITIVE LOGITS
     overlooking
    1.34
     bordering
    1.34
     southwest
    1.29
     inhabited
    1.25
     northeast
    1.23
     situated
    1.23
     northwest
    1.23
     southeast
    1.21
    near
    1.20
     surrounded
    1.18
    Activations Density 0.272%

    No Known Activations