© 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. 7086
    Prev
    Next
    INDEX
    Explanations

    states or regions described as battlegrounds in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to battleground states and undecided voters in the context of elections

    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
    ora
    -0.77
    uthor
    -0.74
    á
    -0.72
    uv
    -0.72
    ager
    -0.70
    QU
    -0.69
    proc
    -0.69
    apore
    -0.69
    ARP
    -0.69
    ews
    -0.68
    POSITIVE LOGITS
     battleground
    1.24
    leground
    0.94
    sburg
    0.91
    sylvania
    0.79
     stronghold
    0.75
     arenas
    0.73
     strongh
    0.72
     chests
    0.72
     Camel
    0.71
     elector
    0.71
    Activations Density 0.014%

    No Known Activations