© 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. 22061
    Prev
    Next
    INDEX
    Explanations

    references to the Star Wars movie titled "The Phantom Menace."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Phantom" in various contexts

    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
    gewater
    -0.85
    minist
    -0.76
    say
    -0.74
    etts
    -0.74
    Interstitial
    -0.72
    eworld
    -0.70
    hiba
    -0.70
    HCR
    -0.70
    ibling
    -0.69
    ternity
    -0.69
    POSITIVE LOGITS
     Stranger
    0.84
     Orchestra
    0.80
    antom
    0.79
     Rider
    0.79
     Horse
    0.79
     Thieves
    0.78
     Phantom
    0.73
     Winged
    0.72
    hawk
    0.72
    oshenko
    0.70
    Activations Density 0.016%

    No Known Activations