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. 17513
    Prev
    Next
    INDEX
    Explanations

    mentions of fraternity-related activities and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to fraternities

    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
     CT
    -0.70
    burn
    -0.70
    days
    -0.67
     Current
    -0.66
     Def
    -0.65
    WIND
    -0.64
    Current
    -0.64
     Maps
    -0.62
    visual
    -0.61
     Wind
    -0.61
    POSITIVE LOGITS
     fraternity
    4.11
     Phi
    1.53
     sor
    1.51
    aternity
    1.37
     Masonic
    1.35
     Kappa
    1.33
     Sigma
    1.06
     communion
    1.05
     Lodge
    1.04
     clubhouse
    1.02
    Activations Density 0.021%

    No Known Activations