© 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. 9696
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "a couple" appears in the text

    oai_token-act-pair · gpt-3.5-turbo
    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
    schild
    -0.77
     Directorate
    -0.70
    endor
    -0.67
    leneck
    -0.67
    sein
    -0.65
    andise
    -0.64
     Receiver
    -0.62
    ulhu
    -0.62
    UME
    -0.60
    roup
    -0.60
    POSITIVE LOGITS
     dozen
    1.24
     hundred
    1.07
    dozen
    1.01
     thousand
    0.86
    days
    0.78
    bars
    0.75
    een
    0.74
    ttes
    0.74
     weeks
    0.74
     of
    0.72
    Activations Density 0.016%

    No Known Activations