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. 9-RES-JB
    6. 4351
    Prev
    Next
    INDEX
    Explanations

    interface elements and actions within a user interface

    oai_token-act-pair · gpt-3.5-turbo

    user interaction and navigation elements related to digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wives
    -0.69
     retirees
    -0.63
    Marcus
    -0.60
     Dietary
    -0.58
    nces
    -0.56
     ][
    -0.56
     rivalry
    -0.56
    ggies
    -0.56
     Lindsey
    -0.55
    isers
    -0.55
    POSITIVE LOGITS
     instantly
    1.12
     prest
    1.11
     toggle
    0.92
     popup
    0.91
     magically
    0.85
     reload
    0.82
     automatically
    0.81
     activates
    0.80
     activate
    0.80
     unlocks
    0.78
    Activations Density 0.281%

    No Known Activations