© 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. 7-RES-JB
    11. 1827
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making in a financial context

    oai_token-act-pair · gpt-3.5-turbo

    consumer behavior and decision-making related to purchases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idable
    -0.66
    ĸļ
    -0.65
    gravity
    -0.64
     Cartoon
    -0.63
    Problem
    -0.63
    Stretch
    -0.62
    Department
    -0.60
     Poe
    -0.59
     Lavrov
    -0.59
    Definition
    -0.59
    POSITIVE LOGITS
     invest
    0.91
     gamble
    0.85
     investing
    0.82
     trusting
    0.78
    xit
    0.78
     voluntarily
    0.77
     buying
    0.77
     investment
    0.76
     buy
    0.73
    untarily
    0.73
    Activations Density 0.575%

    No Known Activations