© 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. 0-RES-JB
    11. 22282
    Prev
    Next
    INDEX
    Explanations

    words related to sewing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the string "wn" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transports
    -0.71
     action
    -0.68
     trains
    -0.66
     sugar
    -0.66
     enzyme
    -0.66
     energetic
    -0.64
     focusing
    -0.63
     accelerator
    -0.63
     entity
    -0.62
     actions
    -0.61
    POSITIVE LOGITS
    wn
    4.66
    wed
    1.55
    WN
    1.36
    ww
    1.36
    ws
    1.34
    wd
    1.11
    wb
    1.08
    wl
    1.05
    wx
    1.03
    Äĩ
    1.01
    Activations Density 0.016%

    No Known Activations