© 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. 8332
    Prev
    Next
    INDEX
    Explanations

    references to ownership or distribution of stocks or assets

    oai_token-act-pair · gpt-3.5-turbo

    references to shares 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
    cher
    -0.72
    icho
    -0.64
    itute
    -0.63
    umper
    -0.62
    killing
    -0.62
    neck
    -0.62
    ensive
    -0.62
    hift
    -0.61
    pecting
    -0.60
    het
    -0.59
    POSITIVE LOGITS
     shares
    3.97
     Shares
    2.59
     share
    2.27
    Shares
    2.15
     stocks
    1.64
    share
    1.61
     Share
    1.43
     sharing
    1.36
     shareholders
    1.30
     SHARES
    1.28
    Activations Density 0.007%

    No Known Activations