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. 9-RES-JB
    6. 6506
    Prev
    Next
    INDEX
    Explanations

    numerical figures related to financial transactions or amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or representations of money and economic figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aggress
    -0.76
     commun
    -0.74
    usalem
    -0.74
    isbury
    -0.72
     posture
    -0.71
     mosqu
    -0.70
     evolving
    -0.69
     epidem
    -0.69
     critically
    -0.69
     encounter
    -0.69
    POSITIVE LOGITS
     ($
    1.22
     Payments
    1.22
    -$
    1.17
     Revenue
    1.13
     Assuming
    1.13
     Costs
    1.12
    $
    1.11
     $
    1.10
    ($
    1.09
     Profit
    1.08
    Activations Density 0.469%

    No Known Activations