© 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. 11-RES-JB
    11. 2025
    Prev
    Next
    INDEX
    Explanations

    phrases related to predictions and financial events, specifically involving the prediction of financial outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to predictions and expectations in economic or financial contexts

    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
     lately
    -0.57
     publishes
    -0.56
     Says
    -0.55
     recent
    -0.55
     complains
    -0.55
    quartered
    -0.53
     Recently
    -0.53
     Compare
    -0.53
     refuses
    -0.53
    */(
    -0.52
    POSITIVE LOGITS
    would
    1.56
     would
    1.52
     wouldn
    1.40
     Would
    1.23
    Would
    1.20
    'd
    1.18
    might
    1.07
     belonged
    1.05
     awaited
    1.01
     might
    0.99
    Activations Density 0.659%

    No Known Activations