© 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. 2-RES-JB
    11. 24145
    Prev
    Next
    INDEX
    Explanations

    mentions of and references to the Southern region or related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "Southern" entities or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icular
    -0.90
    advertising
    -0.79
    LEASE
    -0.74
    icles
    -0.73
    emis
    -0.72
    {"
    -0.71
    icit
    -0.70
    acl
    -0.70
    9999
    -0.68
    UNE
    -0.68
    POSITIVE LOGITS
     Hemisphere
    0.94
     hemisphere
    0.89
     Methodist
    0.80
    western
    0.80
     Southern
    0.78
     Poverty
    0.78
     hospitality
    0.74
    most
    0.72
     Institute
    0.71
    anian
    0.71
    Activations Density 0.008%

    No Known Activations