© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4863
    Prev
    Next
    INDEX
    Explanations

    names of a specific person (Calder) and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names associated with awards and recognition

    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
     Kitty
    -0.69
     fiber
    -0.67
     DNA
    -0.63
    itty
    -0.63
    dq
    -0.62
     fri
    -0.62
    idious
    -0.62
    Hom
    -0.61
    onut
    -0.61
    Lewis
    -0.61
    POSITIVE LOGITS
     Calder
    4.30
     Daly
    1.50
     Berger
    0.92
     Nieto
    0.89
     Erd
    0.88
     Galile
    0.87
     AHL
    0.87
     Clarkson
    0.86
     Caldwell
    0.86
     Pist
    0.85
    Activations Density 0.024%

    No Known Activations