© 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. 6-RES-JB
    11. 7964
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    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
     Mountains
    -0.69
     newsletters
    -0.67
    stood
    -0.65
    arta
    -0.62
     Millions
    -0.62
    Footnote
    -0.60
     HAVE
    -0.60
     conventions
    -0.60
    holders
    -0.59
     IMAGES
    -0.59
    POSITIVE LOGITS
    hes
    1.31
    wolves
    1.00
     originally
    0.98
    hers
    0.94
    wolf
    0.92
    nt
    0.90
     born
    0.90
     initially
    0.89
     instrumental
    0.89
     conceived
    0.88
    Activations Density 0.411%

    No Known Activations