© 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. 17090
    Prev
    Next
    INDEX
    Explanations

    references to events or conditions on a national scale

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "nationwide."

    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
    resses
    -0.74
    rett
    -0.71
     Handler
    -0.71
     Khe
    -0.70
    rette
    -0.67
    rose
    -0.65
    erate
    -0.65
     Brett
    -0.65
    oras
    -0.64
    ÄŁ
    -0.64
    POSITIVE LOGITS
    wide
    1.01
     nationwide
    0.87
    keye
    0.76
    女
    0.75
    irtual
    0.73
     statewide
    0.71
     unemployment
    0.69
     distributed
    0.69
     marketplace
    0.68
     worldwide
    0.68
    Activations Density 0.018%

    No Known Activations