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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10664
    Prev
    Next
    INDEX
    Explanations

    words related to chewing gum

    oai_token-act-pair · gpt-3.5-turbo

    references to gum and actions associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inen
    -0.90
     VIDEOS
    -0.68
     Defenders
    -0.67
    Published
    -0.67
     Levi
    -0.66
    ECH
    -0.65
     Cel
    -0.64
     Victims
    -0.63
    ICS
    -0.63
     Dayton
    -0.62
    POSITIVE LOGITS
     gum
    1.28
    ming
    1.12
    ball
    0.99
    balls
    0.94
     chewing
    0.93
    bled
    0.92
    drops
    0.89
    hib
    0.88
    bo
    0.88
    ble
    0.88
    Activations Density 0.011%

    No Known Activations