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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 20990
    Prev
    Next
    INDEX
    Explanations

    words related to speed or quick action

    oai_token-act-pair · gpt-3.5-turbo

    expressions conveying urgency and feelings of shame or reflection

    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
    nels
    -0.86
    pins
    -0.73
    Spot
    -0.70
    hett
    -0.67
    atell
    -0.63
     Sect
    -0.62
     genres
    -0.62
     Dot
    -0.61
    program
    -0.61
    VID
    -0.60
    POSITIVE LOGITS
     haste
    3.37
    erity
    2.70
     Haste
    1.21
     ashamed
    1.14
     âĨĴ
    1.12
     flashback
    1.00
    ensibly
    0.97
     Vengeance
    0.93
     vengeance
    0.90
     indignation
    0.87
    Activations Density 0.060%

    No Known Activations