© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 22289
    Prev
    Next
    INDEX
    Explanations

    phrases related to printer operations, configurations, and setups

    oai_token-act-pair · gpt-3.5-turbo

    the term "printer" and related references to printers

    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
    ability
    -0.72
     Ak
    -0.71
    wolves
    -0.71
    alo
    -0.70
    Ak
    -0.68
     Season
    -0.67
    olia
    -0.66
    ocial
    -0.65
     Daryl
    -0.64
    bite
    -0.64
    POSITIVE LOGITS
     printer
    3.74
     printers
    3.45
     printing
    1.53
     Printing
    1.48
     scanner
    1.44
     projector
    1.42
     slic
    1.40
     router
    1.39
     modem
    1.36
    printed
    1.31
    Activations Density 0.015%

    No Known Activations