© 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. 20920
    Prev
    Next
    INDEX
    Explanations

    words related to newsletters, email subscriptions, and possibly website sections like 'Editor's Picks'

    oai_token-act-pair · gpt-3.5-turbo

    references to an editor's selections and comments

    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
    utical
    -0.65
    urally
    -0.63
    anian
    -0.62
    kefeller
    -0.59
    irtual
    -0.58
    ttp
    -0.57
    leness
    -0.55
    oan
    -0.52
    eous
    -0.52
    leigh
    -0.51
    POSITIVE LOGITS
    º
    0.57
     Track
    0.52
    ATES
    0.51
    ates
    0.51
    ate
    0.49
    ogs
    0.49
     Extend
    0.49
     Favor
    0.49
     Explain
    0.49
     Head
    0.48
    Activations Density 0.116%

    No Known Activations