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. 3-RES-JB
    6. 11003
    Prev
    Next
    INDEX
    Explanations

    mentions of dairy-related terms, such as specific dairy products or dairy farming

    oai_token-act-pair · gpt-3.5-turbo

    references to dairy and its related industry topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inx
    -0.78
    arters
    -0.69
     Brow
    -0.67
    reads
    -0.66
    umper
    -0.65
     eminent
    -0.64
    andum
    -0.63
    ockets
    -0.63
    ahon
    -0.62
     Pett
    -0.62
    POSITIVE LOGITS
     dairy
    0.99
    bean
    0.90
     Milk
    0.87
     cows
    0.84
    farm
    0.84
     milk
    0.84
    haus
    0.82
     farm
    0.81
    weed
    0.80
    mil
    0.79
    Activations Density 0.006%

    No Known Activations