© 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 EvalsExportsinterp-engineNEWAPI 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. 3793
    Prev
    Next
    INDEX
    Explanations

    Japanese names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically names of individuals

    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
    bee
    -0.89
    achel
    -0.76
     stren
    -0.65
    bees
    -0.64
     camping
    -0.63
     vet
    -0.63
     flowering
    -0.62
    hovah
    -0.62
    raits
    -0.62
    zynski
    -0.61
    POSITIVE LOGITS
    vg
    0.81
     Neh
    0.74
     Garn
    0.73
     Nig
    0.72
    Reason
    0.71
    ãĥ¼ãĥĨ
    0.70
     Drain
    0.68
    rg
    0.67
     Steal
    0.67
     Miliband
    0.67
    Activations Density 0.000%

    No Known Activations