© 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. 4-RES-JB
    11. 22031
    Prev
    Next
    INDEX
    Explanations

    references to a specific quantity, specifically the number "couple"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "couple" used to refer to a small quantity of time or things

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

    No Comments

    Negative Logits
    kinson
    -0.75
    SPONSORED
    -0.74
    ç¥ŀ
    -0.74
     Directorate
    -0.71
    é¾
    -0.70
    ibaba
    -0.69
    ulhu
    -0.69
    schild
    -0.68
    UME
    -0.64
    kefeller
    -0.64
    POSITIVE LOGITS
     dozen
    1.11
    dozen
    0.97
     hundred
    0.96
    zon
    0.75
     thousand
    0.75
     summers
    0.70
    een
    0.69
     wed
    0.68
     goats
    0.67
     thirds
    0.67
    Activations Density 0.014%

    No Known Activations