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. 10-RES-JB
    6. 16916
    Prev
    Next
    INDEX
    Explanations

    information related to employment numbers and workforce statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to large gatherings of people or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibilities
    -0.78
    Appearance
    -0.67
    bert
    -0.60
    perture
    -0.58
    inventoryQuantity
    -0.58
     cont
    -0.58
    bard
    -0.58
    agate
    -0.58
    wcsstore
    -0.57
     NOTICE
    -0.56
    POSITIVE LOGITS
     thousands
    1.73
     millions
    1.61
     tens
    1.60
     hundreds
    1.52
     thousand
    1.39
     lakh
    1.37
     700
    1.36
     800
    1.33
     600
    1.30
     750
    1.30
    Activations Density 1.060%

    No Known Activations