© 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. 9533
    Prev
    Next
    INDEX
    Explanations

    names and titles related to international figures and officials

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals, places, and roles

    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
     tremend
    -0.72
     critical
    -0.66
     sarcastic
    -0.66
     largeDownload
    -0.62
     distinctive
    -0.61
     magnification
    -0.60
     priceless
    -0.60
     cytok
    -0.60
     sudden
    -0.59
     polar
    -0.59
    POSITIVE LOGITS
    ich
    1.03
    ius
    0.98
    eta
    0.91
    ovich
    0.91
    ichi
    0.90
    akis
    0.89
    chuk
    0.88
    inski
    0.88
    ovic
    0.86
    lette
    0.86
    Activations Density 1.144%

    No Known Activations