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

    Neuronpedia

    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. 11298
    Prev
    Next
    INDEX
    Explanations

    words related to financial publications and journalism

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Wall Street."

    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
    imum
    -0.79
    ibilities
    -0.75
    netflix
    -0.75
    ELY
    -0.75
     Horus
    -0.75
    essa
    -0.73
     Uriel
    -0.71
    eworld
    -0.71
    alogue
    -0.70
    menu
    -0.69
    POSITIVE LOGITS
     Journal
    1.33
     firms
    1.14
     bankers
    0.96
     banks
    0.95
     analysts
    0.95
     banker
    0.86
     hedge
    0.83
     brokerage
    0.83
     firm
    0.83
     finan
    0.83
    Activations Density 0.052%

    No Known Activations