© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideas or concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ideas, notions, and propositions

    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
    eni
    -0.64
    emort
    -0.56
     Spoiler
    -0.49
     vulner
    -0.49
    ilan
    -0.49
    aband
    -0.49
     wills
    -0.49
     Fiesta
    -0.48
     Managing
    -0.47
     WARNING
    -0.47
    POSITIVE LOGITS
     that
    1.36
    that
    1.24
     THAT
    0.98
    That
    0.94
     That
    0.92
    orial
    0.74
    uality
    0.72
     thats
    0.66
     of
    0.65
    ²¾
    0.62
    Activations Density 0.181%

    No Known Activations