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. 19570
    Prev
    Next
    INDEX
    Explanations

    references to communities and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "community" in various contexts

    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
    fried
    -0.67
    oof
    -0.67
     seals
    -0.64
     Signed
    -0.64
    lain
    -0.62
     Ago
    -0.62
    fif
    -0.62
    ozy
    -0.61
     Execution
    -0.61
    sei
    -0.60
    POSITIVE LOGITS
     community
    3.48
    community
    2.86
     Community
    2.41
     communities
    2.39
    Community
    2.29
     Communities
    1.86
     neighborhood
    1.61
     ecosystem
    1.54
     neighbourhood
    1.50
     COMMUN
    1.36
    Activations Density 0.032%

    No Known Activations