© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20460
    Prev
    Next
    INDEX
    Explanations

    common names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or situations that cause major changes

    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
     Adds
    -0.76
     externalToEVAOnly
    -0.68
     guiName
    -0.60
     [+
    -0.58
     Starts
    -0.56
    awks
    -0.56
     Written
    -0.56
     Learn
    -0.55
     Flavoring
    -0.55
    */
    -0.54
    POSITIVE LOGITS
     hadn
    1.69
     had
    1.66
    had
    1.59
    Had
    1.29
     would
    1.22
     belonged
    1.22
    'd
    1.20
     depended
    1.18
     existed
    1.16
    would
    1.15
    Activations Density 1.763%

    No Known Activations