© 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. 11168
    Prev
    Next
    INDEX
    Explanations

    the term "mat" (potentially related to "Basmati" in the context of Basmati Blues)

    oai_token-act-pair · gpt-3.5-turbo

    words related to mathematical concepts or terminology

    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
    FUL
    -0.81
    ORD
    -0.70
    BO
    -0.67
    haus
    -0.65
     lightly
    -0.63
    BACK
    -0.62
     contraceptives
    -0.62
    OHN
    -0.61
     DRAG
    -0.60
    OVER
    -0.59
    POSITIVE LOGITS
    hemat
    1.43
    rix
    1.09
    hematic
    1.04
    ches
    0.99
    ters
    0.98
    rals
    0.97
    icians
    0.96
    hematically
    0.95
    ropolitan
    0.91
    urity
    0.88
    Activations Density 0.008%

    No Known Activations