© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13269
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and security, such as "IP," "Q.E.," "environmental protection agency," and "hacked."

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to economic or financial discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ
    -1.15
     âĢ
    -1.06
    âĸº
    -1.04
    ãĢ
    -0.97
    "}],"
    -0.97
    .","
    -0.94
    20439
    -0.90
    »
    -0.87
    âĢIJ
    -0.87
    "},{"
    -0.86
    POSITIVE LOGITS
     hilar
    1.30
     goddamn
    1.29
     crap
    1.28
     kinda
    1.26
     ridiculously
    1.24
     REALLY
    1.24
     freaking
    1.23
     shitty
    1.23
     bullshit
    1.22
     shit
    1.22
    Activations Density 1.716%

    No Known Activations