© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17129
    Prev
    Next
    INDEX
    Explanations

    the name "Zack" and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Zack

    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
    -0.92
    iments
    -0.88
    abulary
    -0.75
    voy
    -0.74
    iment
    -0.72
    duct
    -0.70
    ateurs
    -0.70
    relation
    -0.70
    ional
    -0.70
    milo
    -0.69
    POSITIVE LOGITS
     Whedon
    1.11
     Zack
    1.01
     Snyder
    0.84
     Ryder
    0.83
     Bash
    0.73
     Yamato
    0.73
     Kessler
    0.73
     Dice
    0.73
     Elliott
    0.73
     Mercer
    0.69
    Activations Density 0.016%

    No Known Activations