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. 8-RES-JB
    6. 18761
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters, especially those involving money and feasibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial situations and monetary issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aval
    -0.72
     Oval
    -0.69
     Klu
    -0.68
     Nieto
    -0.67
    ierre
    -0.65
     Halls
    -0.64
    unin
    -0.63
     Width
    -0.61
    osen
    -0.61
    amber
    -0.61
    POSITIVE LOGITS
     ($
    1.03
     incentives
    1.00
    -$
    0.96
     Donation
    0.96
     (£
    0.96
    payer
    0.95
     invested
    0.95
    $$
    0.94
     sponsorship
    0.92
    $$$$
    0.91
    Activations Density 0.210%

    No Known Activations