© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    numbers and codes with a specific structure

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names related to individuals and organizations

    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
    ãĥķãĤ©
    -0.80
    acci
    -0.77
    ement
    -0.72
     Marina
    -0.70
    alty
    -0.68
    anan
    -0.68
    Na
    -0.68
    agascar
    -0.67
    agher
    -0.65
    itect
    -0.65
    POSITIVE LOGITS
     W
    2.13
    W
    2.13
    w
    1.73
     w
    1.65
    Ws
    1.59
    WF
    1.54
     Wis
    1.52
    WN
    1.51
     WM
    1.50
     Wad
    1.49
    Activations Density 0.616%

    No Known Activations