© 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. 0-RES-JB
    11. 13829
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations, particularly focusing on areas with 'South' in their names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "South" in various contexts

    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
    ronic
    -0.72
    anni
    -0.66
     guid
    -0.66
    ogle
    -0.65
    finder
    -0.64
     manifests
    -0.63
    chrome
    -0.62
    Mania
    -0.62
    ogram
    -0.61
    alpha
    -0.61
    POSITIVE LOGITS
     South
    3.44
    South
    3.01
     North
    2.15
    south
    2.15
     Southeast
    2.03
     south
    1.90
    North
    1.88
     Southern
    1.78
     East
    1.76
     Southwest
    1.76
    Activations Density 0.028%

    No Known Activations