© 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. 1-RES-JB
    11. 3437
    Prev
    Next
    INDEX
    Explanations

    mentions of swinging, potentially in a political context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "swing" along with its various contexts

    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
    sis
    -0.72
    bsp
    -0.72
    uf
    -0.69
    xia
    -0.69
    unts
    -0.68
    ISA
    -0.68
    HCR
    -0.67
    resp
    -0.67
     Lauder
    -0.67
    inction
    -0.67
    POSITIVE LOGITS
     swing
    1.31
     Swing
    1.11
     swings
    1.10
     swinging
    1.03
    swing
    1.02
     swung
    0.88
     pend
    0.85
     contrace
    0.78
     traject
    0.76
    tip
    0.75
    Activations Density 0.013%

    No Known Activations