© 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. 10-RES-JB
    11. 3503
    Prev
    Next
    INDEX
    Explanations

    phrases expressing value or importance

    oai_token-act-pair · gpt-3.5-turbo

    evaluative statements about worth or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    but
    -0.87
     But
    -0.72
    But
    -0.67
    eatured
    -0.66
    hari
    -0.62
    ructose
    -0.62
    BUT
    -0.61
    schild
    -0.60
    ornia
    -0.60
     but
    -0.59
    POSITIVE LOGITS
     nonetheless
    1.85
     anyway
    1.14
     nevertheless
    1.10
     anyways
    1.05
    etheless
    1.05
     owing
    0.87
    .
    0.82
     insofar
    0.82
     because
    0.81
    .[
    0.77
    Activations Density 0.951%

    No Known Activations