© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    onomatopoeic words related to bubbling or bubbling-like sounds

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bub" and its variations, which appear to be related to a specific theme or topic possibly linked to "bubbles" or "bubbling."

    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
     Duty
    -0.70
    sson
    -0.70
    WARD
    -0.69
    SAY
    -0.69
    ãĥĥãĥī
    -0.69
    ãĥĩãĤ£
    -0.68
     VIDE
    -0.68
    IVES
    -0.67
     Sax
    -0.66
    istant
    -0.66
    POSITIVE LOGITS
    bly
    1.09
     bub
    1.09
    bles
    0.98
    bling
    0.97
    bled
    0.95
    bub
    0.89
    lio
    0.82
     champagne
    0.81
    anqu
    0.79
    ilant
    0.77
    Activations Density 0.005%

    No Known Activations