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. 1-RES-JB
    6. 6153
    Prev
    Next
    INDEX
    Explanations

    quantities of items mentioned in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and amounts of items or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Harris
    -0.80
    scape
    -0.69
    OVA
    -0.69
    lich
    -0.68
    CTV
    -0.66
    rip
    -0.65
    bid
    -0.65
    line
    -0.64
    Buzz
    -0.63
     Story
    -0.63
    POSITIVE LOGITS
    paces
    1.13
    omething
    1.11
    poons
    1.11
     quantities
    1.04
    ynthesis
    1.03
    uggest
    1.02
    ometimes
    0.98
     amounts
    0.95
     gobl
    0.95
    ourcing
    0.93
    Activations Density 0.032%

    No Known Activations