© 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. 11-RES-JB
    11. 6997
    Prev
    Next
    INDEX
    Explanations

    words related to elections and politics

    oai_token-act-pair · gpt-3.5-turbo

    details about election results and victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Crew
    -0.76
     VIDEOS
    -0.70
    ahi
    -0.65
     Huss
    -0.65
     References
    -0.62
    future
    -0.60
    Entry
    -0.60
    ":["
    -0.60
    camp
    -0.59
    emis
    -0.58
    POSITIVE LOGITS
     landslide
    1.34
     decisively
    1.18
     overwhelmingly
    1.14
     narrowly
    1.14
     turnout
    1.10
     landsl
    1.08
     elector
    1.05
     defeating
    1.05
     primaries
    1.04
     convinc
    1.02
    Activations Density 0.250%

    No Known Activations