© 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. 6-RES-JB
    11. 10775
    Prev
    Next
    INDEX
    Explanations

    the word "swing" along with related terms in the context of elections and movements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "swing" and its variations related to political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.78
    士
    -0.75
    sis
    -0.74
    xia
    -0.74
    iary
    -0.70
    resp
    -0.70
    inction
    -0.68
    unts
    -0.68
    aneous
    -0.67
    HCR
    -0.67
    POSITIVE LOGITS
     swing
    0.93
     swinging
    0.89
     pend
    0.87
     swings
    0.86
     Swing
    0.84
    tip
    0.77
    mill
    0.77
    yip
    0.77
    shape
    0.75
     swung
    0.74
    Activations Density 0.024%

    No Known Activations