© 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. 7261
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "turmeric."

    oai_token-act-pair · gpt-3.5-turbo

    references to "tur" and related terms, likely focusing on turkeys or dishes containing turkey

    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
     Sacrament
    -0.77
     Known
    -0.72
     Recovery
    -0.71
     Corrections
    -0.71
     Physicians
    -0.71
    isSpecialOrderable
    -0.69
     Safe
    -0.69
    soDeliveryDate
    -0.69
     Copenhagen
    -0.68
    ãģ®éŃĶ
    -0.67
    POSITIVE LOGITS
    kish
    1.23
    fing
    1.02
    meric
    0.99
    teenth
    0.99
    rible
    0.98
    itage
    0.97
    onto
    0.96
    rette
    0.94
    pid
    0.94
     tur
    0.92
    Activations Density 0.003%

    No Known Activations