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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 2-RES-JB
    6. 22648
    Prev
    Next
    INDEX
    Explanations

    words related to stoves and cooking appliances

    oai_token-act-pair · gpt-3.5-turbo

    references to cooking appliances and utensils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Byrne
    -0.83
    aird
    -0.70
    rity
    -0.68
    oral
    -0.67
    ados
    -0.67
    orns
    -0.66
    oria
    -0.66
    eme
    -0.66
    ually
    -0.65
     vectors
    -0.65
    POSITIVE LOGITS
     stove
    1.27
     burner
    1.18
     cooker
    1.14
    pipe
    0.99
    sonian
    0.93
     kettle
    0.88
     oven
    0.86
     cook
    0.86
     grill
    0.86
    washer
    0.84
    Activations Density 0.023%

    No Known Activations