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. 10747
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions and monetary values

    oai_token-act-pair · gpt-3.5-turbo

    terms related to costs and economic 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
    âĦ¢:
    -0.95
    Kyle
    -0.87
    FOX
    -0.79
    maxwell
    -0.79
    ********************************
    -0.78
    ®,
    -0.77
    Guest
    -0.75
    umblr
    -0.74
    ................................
    -0.74
     (&
    -0.74
    POSITIVE LOGITS
     âĤ¬
    1.22
     euros
    1.14
     Bulgarian
    1.07
     UNESCO
    1.04
     Luxembourg
    1.04
     Hungary
    1.04
     Bulgaria
    1.04
     Jakarta
    1.02
     Sloven
    1.01
     Romanian
    1.01
    Activations Density 1.177%

    No Known Activations