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. 10-RES-JB
    6. 15660
    Prev
    Next
    INDEX
    Explanations

    financial amounts or figures in euros or yen

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.79
    opic
    -0.68
     Niagara
    -0.67
    isSpecialOrderable
    -0.64
    istical
    -0.63
     Sabbath
    -0.61
    sonian
    -0.60
     Chattanooga
    -0.59
     McKenzie
    -0.59
    Bey
    -0.59
    POSITIVE LOGITS
     (£
    1.65
     ($
    1.55
     (~
    1.18
     apiece
    1.04
    USD
    1.01
    ($
    1.00
     euros
    0.98
     sterling
    0.98
     USD
    0.97
    pees
    0.97
    Activations Density 0.119%

    No Known Activations