© 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. 0-RES-JB
    11. 13261
    Prev
    Next
    INDEX
    Explanations

    percentages represented as numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages

    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
    HUD
    -0.70
    hee
    -0.68
     SB
    -0.66
    bnb
    -0.66
    wine
    -0.65
    shall
    -0.64
     Spoiler
    -0.62
    akov
    -0.62
    HR
    -0.62
     retaliate
    -0.60
    POSITIVE LOGITS
     cent
    4.14
     Cent
    2.08
    cent
    2.06
    Cent
    1.85
    CENT
    1.78
     CENT
    1.44
     centered
    1.31
     centres
    1.31
    icent
    1.30
     penny
    1.23
    Activations Density 0.028%

    No Known Activations