© 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. 2-RES-JB
    11. 22543
    Prev
    Next
    INDEX
    Explanations

    proper names of people, potentially celebrities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and terms related to individuals and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaz
    -0.82
    umar
    -0.76
    pling
    -0.75
    plings
    -0.74
    ktop
    -0.72
     Horus
    -0.72
    metry
    -0.71
    owship
    -0.69
    holders
    -0.69
    weed
    -0.68
    POSITIVE LOGITS
    ework
    0.77
    issance
    0.76
    ype
    0.76
    ãĥĥãĥĪ
    0.74
    ingham
    0.72
    orate
    0.71
    ãĤ¡
    0.70
    eful
    0.69
    esy
    0.69
    eur
    0.69
    Activations Density 0.018%

    No Known Activations