© 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. 12238
    Prev
    Next
    INDEX
    Explanations

    words related to grapes and winemaking

    oai_token-act-pair · gpt-3.5-turbo

    mentions of grapes

    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
    clus
    -0.72
    favorite
    -0.70
    seq
    -0.69
    clusive
    -0.68
    icio
    -0.65
     ay
    -0.65
     sterling
    -0.65
    soDeliveryDate
    -0.64
     DK
    -0.63
     unconditional
    -0.63
    POSITIVE LOGITS
     Grape
    1.11
    raviolet
    0.79
    olester
    0.73
    criminal
    0.67
    bilt
    0.66
     Torrent
    0.63
    ricanes
    0.63
    arette
    0.62
    mson
    0.60
    wagen
    0.59
    Activations Density 0.000%

    No Known Activations