© 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. 7788
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names like "Andre" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Andre."

    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
    inct
    -0.96
    ulhu
    -0.80
    manship
    -0.74
    lishing
    -0.73
    stakes
    -0.71
    ointed
    -0.68
    plain
    -0.67
    yrinth
    -0.65
    lied
    -0.65
    lished
    -0.65
    POSITIVE LOGITS
    tti
    1.14
    essen
    0.91
    byss
    0.82
    cats
    0.78
     Andre
    0.78
     Gord
    0.72
     Paste
    0.71
     XIII
    0.69
    aic
    0.68
    idis
    0.67
    Activations Density 0.023%

    No Known Activations