© 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. 17230
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names, possibly related to locations or people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Rockefeller and Morgenthau families

    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
    shapeshifter
    -0.74
     Buffy
    -0.68
     Plato
    -0.66
     Wonderland
    -0.66
     Syri
    -0.65
    netflix
    -0.64
    most
    -0.64
     fluorescent
    -0.63
     debtor
    -0.61
     Hasan
    -0.61
    POSITIVE LOGITS
    helle
    1.29
    kefeller
    1.11
    atell
    1.06
    enthal
    0.96
    kef
    0.95
    hett
    0.91
    bons
    0.89
    afort
    0.88
    hester
    0.87
     Roc
    0.83
    Activations Density 0.015%

    No Known Activations