© 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. 10-RES-JB
    11. 8512
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Our"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "our."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conom
    -0.85
    puff
    -0.80
    tar
    -0.71
     outwe
    -0.68
    hift
    -0.67
    arth
    -0.66
    abl
    -0.65
    uls
    -0.64
    icter
    -0.63
    esson
    -0.63
    POSITIVE LOGITS
    selves
    1.30
     own
    1.03
     hearts
    1.01
     ancestors
    0.95
     beloved
    0.94
     heroine
    0.93
     selves
    0.92
     brains
    0.91
     asses
    0.91
     dear
    0.91
    Activations Density 0.136%

    No Known Activations