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. 11-RES-JB
    6. 8126
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mobile and data plans

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and business transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Klopp
    -0.99
    byn
    -0.89
     Dwarf
    -0.88
     paintings
    -0.86
     Dwar
    -0.83
     Pyth
    -0.82
     painting
    -0.80
     Jaune
    -0.79
     Severus
    -0.79
     Witches
    -0.79
    POSITIVE LOGITS
     Verizon
    1.98
     Sprint
    1.95
     LTE
    1.86
     carriers
    1.78
     carrier
    1.69
     wireless
    1.56
     Cellular
    1.55
     Wireless
    1.52
     prepaid
    1.43
     AT
    1.39
    Activations Density 0.275%

    No Known Activations