© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14578
    Prev
    Next
    INDEX
    Explanations

    mentions of potatoes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of potatoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.85
    olulu
    -0.83
    inances
    -0.81
    utenberg
    -0.80
    herty
    -0.79
    lasses
    -0.78
    anwhile
    -0.78
    eanor
    -0.77
    stract
    -0.75
    uckland
    -0.75
    POSITIVE LOGITS
     starch
    1.04
     potato
    0.96
     chips
    0.94
     potatoes
    0.93
     salad
    0.90
    assium
    0.89
    atoes
    0.87
     peel
    0.83
     Tart
    0.81
    cake
    0.80
    Activations Density 0.014%

    No Known Activations