© 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. 11-RES-JB
    11. 9852
    Prev
    Next
    INDEX
    Explanations

    financial terms and trends in relation to market movements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to market predictions and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Correctional
    -0.76
    Assistant
    -0.75
     Campus
    -0.74
    unte
    -0.73
     Citizenship
    -0.72
     voic
    -0.71
     multicultural
    -0.69
    letal
    -0.68
     Brennan
    -0.68
    Assembly
    -0.67
    POSITIVE LOGITS
     bullish
    1.67
     volatility
    1.64
     liquidity
    1.45
     traders
    1.36
     trading
    1.36
     valuation
    1.31
    iquid
    1.31
     price
    1.30
     stocks
    1.28
    stocks
    1.25
    Activations Density 0.593%

    No Known Activations