© 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. 7252
    Prev
    Next
    INDEX
    Explanations

    mentions of a musical duo

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group of two individuals or entities, commonly labeled as a "duo."

    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
    cock
    -0.71
    iken
    -0.65
    gun
    -0.63
     saline
    -0.63
    orie
    -0.63
    tml
    -0.61
    lesi
    -0.61
    ugu
    -0.61
    renheit
    -0.60
    ylon
    -0.60
    POSITIVE LOGITS
     duo
    0.99
     mates
    0.81
     Duo
    0.74
    footed
    0.74
    peak
    0.73
    ãĤ¼
    0.66
    kson
    0.66
     mate
    0.66
     halves
    0.65
    jen
    0.65
    Activations Density 0.024%

    No Known Activations