© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 11300
    Prev
    Next
    INDEX
    Explanations

    terms indicating support or advocacy for a cause

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to support, representation, and advocacy

    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
    ĻĤ
    -0.58
     Rebell
    -0.56
    bye
    -0.53
    EMS
    -0.51
    XP
    -0.50
    anned
    -0.49
    ŃĶ
    -0.49
     Constantin
    -0.48
    ippery
    -0.48
     outp
    -0.48
    POSITIVE LOGITS
     of
    1.26
     thereof
    1.26
    of
    1.01
    Of
    0.95
     OF
    0.94
     Of
    0.91
    OF
    0.78
    oft
    0.77
    ance
    0.70
    aldehyde
    0.69
    Activations Density 0.118%

    No Known Activations