© 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. 5729
    Prev
    Next
    INDEX
    Explanations

    names and terms related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reproductive rights and legal terminology

    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
    Ô
    -1.02
     slicing
    -0.85
    ptroller
    -0.84
    ouble
    -0.83
    scill
    -0.82
     algorith
    -0.81
     Rosenstein
    -0.78
    Rh
    -0.78
     slice
    -0.77
     mathemat
    -0.75
    POSITIVE LOGITS
     Camp
    2.63
    Camp
    2.62
    camp
    2.25
     camp
    2.24
     camps
    2.04
     Campbell
    2.01
     camping
    1.77
     tents
    1.40
     encamp
    1.27
     cam
    1.23
    Activations Density 0.184%

    No Known Activations