© 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. 0-RES-JB
    11. 5101
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial stakeholders or shareholders

    oai_token-act-pair · gpt-3.5-turbo

    references to stakeholders or holders in a financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geek
    -0.65
     avatar
    -0.62
     son
    -0.62
     archae
    -0.61
    actor
    -0.61
     person
    -0.61
     ton
    -0.60
     athlete
    -0.60
     blur
    -0.59
     robot
    -0.59
    POSITIVE LOGITS
    holders
    3.98
     holders
    2.06
    owners
    1.48
     shareholders
    1.47
    wives
    1.35
    seekers
    1.35
    payers
    1.34
    writers
    1.33
    holder
    1.25
     creditors
    1.17
    Activations Density 0.028%

    No Known Activations