Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3688
    Prev
    Next
    INDEX
    Explanations

    cooking instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to cooking and food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.66
    emale
    -0.65
    furt
    -0.65
    ombat
    -0.64
    DN
    -0.63
    iami
    -0.60
     Labrador
    -0.60
    ibur
    -0.60
    official
    -0.60
    Ly
    -0.60
    POSITIVE LOGITS
    riger
    0.79
     Tables
    0.78
     remaining
    0.75
     excess
    0.73
    zzle
    0.73
     remainder
    0.72
     freezer
    0.70
     parchment
    0.70
     evenly
    0.70
     yeast
    0.70
    Activations Density 0.093%

    No Known Activations