© 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. 6-RES-JB
    11. 3587
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ba"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity named "Ba."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessly
    -0.88
    wise
    -0.86
    LAND
    -0.73
    PORT
    -0.73
    otle
    -0.73
    lessness
    -0.71
    ments
    -0.71
    matic
    -0.70
    mented
    -0.69
    MENT
    -0.66
    POSITIVE LOGITS
    uble
    1.00
    atar
    0.96
    uman
    0.89
    umann
    0.88
    Ba
    0.85
    ison
    0.83
    iting
    0.81
    ild
    0.81
    plin
    0.80
    etooth
    0.80
    Activations Density 0.018%

    No Known Activations