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. 2-RES-JB
    6. 22864
    Prev
    Next
    INDEX
    Explanations

    Greek alphabet letters, particularly those related to fraternities or brand names

    oai_token-act-pair · gpt-3.5-turbo

    references to Greek life organizations and their associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¢ãĥ«
    -0.86
    esome
    -0.82
    enegger
    -0.79
    iflower
    -0.79
    taboola
    -0.78
    ulatory
    -0.78
    urers
    -0.77
    PsyNetMessage
    -0.77
    */(
    -0.77
    puter
    -0.76
    POSITIVE LOGITS
     Centauri
    1.32
     Sigma
    1.01
     Gamma
    0.98
     Phi
    0.94
     Eps
    0.91
    ilon
    0.91
     Beta
    0.90
     Tau
    0.89
     Scotia
    0.86
     Nu
    0.86
    Activations Density 0.012%

    No Known Activations