© 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. 4-RES-JB
    11. 4823
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially their first names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those of individuals

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

    No Comments

    Negative Logits
    Interstitial
    -0.66
    emale
    -0.62
     undermin
    -0.54
    ../
    -0.53
    chnology
    -0.52
    ãĥ¼ãĥĨ
    -0.52
    ntil
    -0.52
    milo
    -0.52
    arettes
    -0.51
    shapeshifter
    -0.51
    POSITIVE LOGITS
     Reed
    0.71
     Rice
    0.68
     Alexander
    0.68
     Roberts
    0.68
     Wright
    0.66
     Foster
    0.65
     Jenkins
    0.65
     Patrick
    0.65
     Clarke
    0.65
     Butler
    0.64
    Activations Density 0.393%

    No Known Activations