© 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. 12403
    Prev
    Next
    INDEX
    Explanations

    references to an individual's personal opinion or sentiment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this."

    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
    Ĵ
    -0.89
    Ĭ±
    -0.86
    izontal
    -0.86
    ĸļ
    -0.81
    İĭ
    -0.80
    icons
    -0.79
    quarters
    -0.77
    ±
    -0.77
    Ķ
    -0.76
    ļé
    -0.76
    POSITIVE LOGITS
     guy
    1.11
     particular
    1.07
     stuff
    1.02
     shit
    0.99
     sucker
    0.97
     crap
    0.94
     thing
    0.94
     shenan
    0.91
     whole
    0.90
     stupid
    0.90
    Activations Density 0.146%

    No Known Activations