© 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. 10-RES-JB
    11. 5964
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or declaration, such as confessing, proclaiming, and explaining

    oai_token-act-pair · gpt-3.5-turbo

    actions related to declaring or confessing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.71
    luster
    -0.70
    @#&
    -0.65
    taboola
    -0.65
    asus
    -0.65
    enium
    -0.62
     subur
    -0.60
    sites
    -0.59
    asse
    -0.59
    agues
    -0.59
    POSITIVE LOGITS
     aloud
    1.10
     how
    1.09
     why
    1.03
     loudly
    0.98
     oneself
    0.97
     whether
    0.92
     beforehand
    0.92
     allegiance
    0.91
     truths
    0.90
     that
    0.89
    Activations Density 0.243%

    No Known Activations