© 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. 2-RES-JB
    11. 12750
    Prev
    Next
    INDEX
    Explanations

    words related to transformation or evolution

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "become."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.71
     rug
    -0.71
    tsky
    -0.66
     uphill
    -0.64
    DER
    -0.63
     TN
    -0.58
     antic
    -0.58
     belt
    -0.58
     Mankind
    -0.58
     Gong
    -0.58
    POSITIVE LOGITS
    oming
    1.09
    leans
    1.07
    bec
    1.03
    uity
    0.99
    zek
    0.95
    isons
    0.93
    racuse
    0.90
    imil
    0.87
    clair
    0.87
    uous
    0.85
    Activations Density 0.004%

    No Known Activations