© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15537
    Prev
    Next
    INDEX
    Explanations

    items associated with brushes, such as "brush tool," "mixing bowl," and "paint brush."

    oai_token-act-pair · gpt-3.5-turbo

    references to brushes and their various uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oy
    -0.81
     Chancellor
    -0.73
     Mald
    -0.73
    Oracle
    -0.72
    XXX
    -0.71
    LD
    -0.69
     Atkins
    -0.68
     Equality
    -0.67
     Oracle
    -0.66
     FreeBSD
    -0.64
    POSITIVE LOGITS
     brush
    4.08
     brushes
    3.00
    brush
    2.85
     Brush
    2.79
     brushing
    1.98
     brushed
    1.73
     Brus
    1.61
     brist
    1.49
     scrub
    1.21
     lash
    1.20
    Activations Density 0.017%

    No Known Activations