© 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. 11-RES-JB
    11. 16519
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to distinctive characteristics of counties or regions

    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
    ipedia
    -0.83
    ileaks
    -0.74
    NASA
    -0.73
    Actor
    -0.73
     halftime
    -0.72
    World
    -0.71
    YouTube
    -0.71
    NSA
    -0.71
    NFL
    -0.71
    tools
    -0.70
    POSITIVE LOGITS
     districts
    1.78
     counties
    1.71
     suburbs
    1.57
     municipalities
    1.56
     precincts
    1.48
     towns
    1.47
     regions
    1.46
     neighbourhoods
    1.45
     areas
    1.45
     Areas
    1.40
    Activations Density 0.422%

    No Known Activations