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. 7-RES-JB
    6. 17043
    Prev
    Next
    INDEX
    Explanations

    software bug-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    issues related to software bugs and fixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.80
    ONSORED
    -0.75
    adies
    -0.74
    anooga
    -0.72
    —-
    -0.70
    sonian
    -0.68
     proponent
    -0.68
    "—
    -0.66
    education
    -0.66
    ocrats
    -0.65
    POSITIVE LOGITS
     respawn
    1.08
     tooltip
    1.03
     overwrite
    1.00
     UI
    0.91
     GUI
    0.90
     incorrectly
    0.87
     reload
    0.87
     animations
    0.87
     Magicka
    0.86
     Animation
    0.85
    Activations Density 0.312%

    No Known Activations