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. 3815
    Prev
    Next
    INDEX
    Explanations

    words related to financial metrics and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    metrics and data related to performance and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ocrat
    -0.81
    ©¶æ
    -0.75
    mad
    -0.74
    ulhu
    -0.71
    Modern
    -0.70
    usky
    -0.69
    west
    -0.68
    ocratic
    -0.68
     Democr
    -0.68
    western
    -0.68
    POSITIVE LOGITS
     GDP
    1.40
     productivity
    1.31
     profitability
    1.28
     throughput
    1.22
     efficiency
    1.21
     percentage
    1.20
     frequency
    1.19
     density
    1.19
     income
    1.18
     earnings
    1.16
    Activations Density 0.261%

    No Known Activations