© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to institutions, technology, and projects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data and analysis

    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
    until
    -0.67
    untarily
    -0.62
    Rated
    -0.59
    rahim
    -0.58
    before
    -0.57
     Slowly
    -0.56
    poral
    -0.55
    even
    -0.55
     }}
    -0.54
     msec
    -0.54
    POSITIVE LOGITS
     being
    0.81
     itself
    0.74
     aforementioned
    0.73
     looming
    0.73
     however
    0.71
    ,
    0.71
     appearing
    0.71
     mentioned
    0.70
    *,
    0.70
     seeming
    0.70
    Activations Density 0.296%

    No Known Activations