© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 24083
    Prev
    Next
    INDEX
    Explanations

    mentions of musical duos

    oai_token-act-pair · gpt-3.5-turbo

    mentions of musical duos or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cock
    -0.81
    orie
    -0.70
    ugu
    -0.69
    ylon
    -0.67
    lite
    -0.66
    latable
    -0.66
    vantage
    -0.65
    ijing
    -0.65
    ady
    -0.64
    iken
    -0.63
    POSITIVE LOGITS
     duo
    1.07
     Duo
    0.79
     mates
    0.75
     comed
    0.73
    footed
    0.68
    kson
    0.66
    peak
    0.66
     mate
    0.65
    ãĤ¼
    0.65
     tandem
    0.63
    Activations Density 0.013%

    No Known Activations