© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    mention of the ingredient 'flour' in baking recipes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flour."

    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
    76561
    -0.86
    nesota
    -0.70
     Ones
    -0.68
    SPONSORED
    -0.67
    >>>>>>>>
    -0.65
     Defenders
    -0.64
    Lear
    -0.62
     Proxy
    -0.62
     SAP
    -0.62
    tnc
    -0.62
    POSITIVE LOGITS
    ishes
    1.18
    meal
    0.94
    ishing
    0.93
    ishment
    0.93
     flour
    0.92
    ished
    0.82
     mills
    0.79
    less
    0.79
    orescent
    0.76
     pastry
    0.76
    Activations Density 0.006%

    No Known Activations