© 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
    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. 14833
    Prev
    Next
    INDEX
    Explanations

    words related to publishing or publishers

    oai_token-act-pair · gpt-3.5-turbo

    references to "publisher"

    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
     drills
    -0.73
     drilled
    -0.71
     Drill
    -0.67
    zona
    -0.65
     Vent
    -0.64
    aux
    -0.62
    Ability
    -0.60
    wreck
    -0.60
    mares
    -0.59
     Kali
    -0.58
    POSITIVE LOGITS
     publisher
    3.72
     publishers
    3.35
     Publishers
    2.48
    Publisher
    2.48
     Publisher
    2.44
     publishing
    2.12
     Publishing
    1.88
     editors
    1.68
    lisher
    1.67
     publish
    1.63
    Activations Density 0.015%

    No Known Activations