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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6188
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial analysis and market research

    oai_token-act-pair · gpt-3.5-turbo

    references to analysts and financial commentary

    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
    ĸļ
    -0.76
     Volunteers
    -0.75
     traumatic
    -0.74
     deport
    -0.72
    interstitial
    -0.71
    aepernick
    -0.71
    SPONSORED
    -0.70
     Lovecraft
    -0.70
    Mods
    -0.69
     indoctr
    -0.69
    POSITIVE LOGITS
     analyst
    1.59
     analysts
    1.37
     consultancy
    1.35
     forecasting
    1.34
     Markets
    1.32
    alyst
    1.31
     Analyst
    1.24
     forecasts
    1.21
     bullish
    1.21
     brokerage
    1.21
    Activations Density 0.379%

    No Known Activations