© 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. 4-RES-JB
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, specifically the Southern region

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Southern."

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

    No Comments

    Negative Logits
    icular
    -0.87
    icit
    -0.78
    icles
    -0.73
    endi
    -0.73
    /**
    -0.73
    acl
    -0.73
    advertising
    -0.72
    emis
    -0.72
    enable
    -0.72
    uably
    -0.69
    POSITIVE LOGITS
     Hemisphere
    1.07
     hemisphere
    0.86
    western
    0.84
     Poverty
    0.82
    anian
    0.76
     Belle
    0.75
     Methodist
    0.75
     Isles
    0.75
     hospitality
    0.74
     Railway
    0.74
    Activations Density 0.010%

    No Known Activations