© 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. 7-RES-JB
    11. 10011
    Prev
    Next
    INDEX
    Explanations

    dates or references to historical events

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrases or concepts expressed with variations of "it’s."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reception
    -0.63
     exhib
    -0.61
     Unic
    -0.61
    erning
    -0.61
    eln
    -0.61
     Juda
    -0.60
     favourite
    -0.56
     Glou
    -0.54
     fixture
    -0.54
     radial
    -0.54
    POSITIVE LOGITS
    ymes
    1.13
    acca
    0.86
    erest
    0.84
    ook
    0.78
    ebook
    0.78
    ¬
    0.76
    ¢
    0.75
    º
    0.75
    ¼
    0.74
    ¯
    0.73
    Activations Density 0.210%

    No Known Activations