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. 20637
    Prev
    Next
    INDEX
    Explanations

    terms related to significant changes or improvements happening in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overhaul" and its variations, indicating a focus on significant changes or reforms

    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
    idences
    -0.73
    false
    -0.64
     Participant
    -0.62
    cause
    -0.62
    Cause
    -0.62
    mi
    -0.61
    occ
    -0.60
    ileged
    -0.60
    God
    -0.60
     Kaf
    -0.60
    POSITIVE LOGITS
     overhaul
    3.63
     redesign
    1.85
     revamped
    1.65
     remod
    1.55
     reorgan
    1.54
     reform
    1.45
     restructuring
    1.45
     rewrite
    1.35
     redesigned
    1.34
     rebuild
    1.33
    Activations Density 0.011%

    No Known Activations