© 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. 1-RES-JB
    6. 23117
    Prev
    Next
    INDEX
    Explanations

    names and terms containing the sequence "rice."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or term related to "rice."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sevent
    -0.65
     pioneering
    -0.60
    otom
    -0.60
     Sunshine
    -0.58
     hemp
    -0.58
    kers
    -0.57
     struct
    -0.57
     sheriff
    -0.57
     Presidents
    -0.56
     lit
    -0.56
    POSITIVE LOGITS
    rice
    1.35
    zza
    0.95
    utical
    0.92
     cooker
    0.91
    lli
    0.89
    llular
    0.88
    ption
    0.87
    cules
    0.84
    mson
    0.84
    llo
    0.82
    Activations Density 0.004%

    No Known Activations