© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12663
    Prev
    Next
    INDEX
    Explanations

    economic terms and financial indicators

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic and market conditions

    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
    Names
    -0.80
    eyes
    -0.74
    KA
    -0.74
    ãĤ±
    -0.72
    ograp
    -0.71
    js
    -0.71
    abulary
    -0.70
    cking
    -0.69
    icus
    -0.69
    vic
    -0.68
    POSITIVE LOGITS
     rising
    1.31
     increased
    1.31
     declining
    1.29
     recession
    1.27
     reductions
    1.26
     globalization
    1.26
     increases
    1.24
     declines
    1.24
     decreased
    1.22
     decreasing
    1.21
    Activations Density 0.340%

    No Known Activations