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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 15619
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic regions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laughter
    -0.91
    ERA
    -0.87
    software
    -0.81
    DragonMagazine
    -0.78
    rob
    -0.77
     Turing
    -0.76
    EVA
    -0.74
    kind
    -0.74
    ERROR
    -0.72
    dylib
    -0.71
    POSITIVE LOGITS
     northern
    1.50
     southwestern
    1.47
     northeastern
    1.45
     southern
    1.44
     southeastern
    1.42
     coastal
    1.42
     northwestern
    1.41
     inland
    1.39
     eastern
    1.39
     southwest
    1.36
    Activations Density 0.228%

    No Known Activations