© 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. 1-RES-JB
    11. 24022
    Prev
    Next
    INDEX
    Explanations

    words related to political battlegrounds

    oai_token-act-pair · gpt-3.5-turbo

    references to election battlegrounds or undecided voters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ever
    -0.72
    occ
    -0.72
    ISA
    -0.71
    QU
    -0.71
    ARP
    -0.70
    ires
    -0.69
    uv
    -0.69
    uffle
    -0.67
    ews
    -0.67
    arin
    -0.65
    POSITIVE LOGITS
     battleground
    1.44
    leground
    1.10
    sburg
    0.98
     arenas
    0.87
    sylvania
    0.78
     swing
    0.76
    halla
    0.74
     elector
    0.73
     strongh
    0.73
     stronghold
    0.72
    Activations Density 0.008%

    No Known Activations