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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20061
    Prev
    Next
    INDEX
    Explanations

    references to bubbles or bubbling

    oai_token-act-pair · gpt-3.5-turbo

    words related to bubbling or effervescent substances, particularly in a metaphorical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.75
    SAY
    -0.73
    ALLY
    -0.70
     Duty
    -0.70
    ãĥĥãĥī
    -0.66
    QUIRE
    -0.66
    IVES
    -0.66
    IVE
    -0.65
     Sax
    -0.64
    ãĥĨãĤ£
    -0.64
    POSITIVE LOGITS
     bub
    1.10
    bly
    1.02
    bled
    0.97
    bling
    0.95
    bles
    0.92
    bub
    0.92
    anqu
    0.84
    lio
    0.83
     champagne
    0.81
    toc
    0.76
    Activations Density 0.010%

    No Known Activations