© 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. 4890
    Prev
    Next
    INDEX
    Explanations

    phrases related to military invasions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" and related discussions of historical events or 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
     partName
    -0.81
    picture
    -0.80
    ringe
    -0.78
    soType
    -0.76
    ples
    -0.73
    ensical
    -0.72
    eus
    -0.71
    vana
    -0.69
    paren
    -0.69
    oux
    -0.69
    POSITIVE LOGITS
     Chilean
    0.71
     brig
    0.66
     course
    0.65
     Bengal
    0.65
     virginity
    0.64
     Mum
    0.63
     Gaza
    0.63
     Normandy
    0.62
     Goods
    0.62
     Northern
    0.62
    Activations Density 0.243%

    No Known Activations