© 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. 0-RES-JB
    11. 5352
    Prev
    Next
    INDEX
    Explanations

    mentions of a pair of individuals, likely working together as a duo

    oai_token-act-pair · gpt-3.5-turbo

    references to musical or performance groups consisting of two or more members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    internal
    -0.72
    ATIONAL
    -0.65
    afety
    -0.65
     [-
    -0.62
     Measure
    -0.62
    chwitz
    -0.61
    ARB
    -0.61
     Estimates
    -0.61
    burning
    -0.60
    Newsletter
    -0.59
    POSITIVE LOGITS
     duo
    3.73
     trio
    2.87
     Duo
    1.89
     pair
    1.88
     tandem
    1.66
     pairing
    1.63
     quart
    1.44
     twins
    1.38
     combo
    1.35
     couple
    1.27
    Activations Density 0.023%

    No Known Activations