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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 9434
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Has" followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "Has" indicating possession, action, or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mercury
    -0.71
     takedown
    -0.68
    eering
    -0.68
     primates
    -0.64
     Tropical
    -0.63
    æĢ
    -0.62
     lining
    -0.60
    andering
    -0.60
    aneous
    -0.60
     pole
    -0.60
    POSITIVE LOGITS
    kell
    1.16
    linger
    1.00
     Been
    0.95
    bro
    0.91
    lem
    0.90
    fred
    0.90
    been
    0.89
    endor
    0.88
    lington
    0.87
    merga
    0.86
    Activations Density 0.007%

    No Known Activations