© 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. 8503
    Prev
    Next
    INDEX
    Explanations

    the name "Mattis" and "Connor"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, especially in a military or leadership context

    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
    llah
    -0.79
     Gohan
    -0.74
    Sund
    -0.74
    ttle
    -0.72
    plane
    -0.71
    Clock
    -0.71
    birth
    -0.71
    bral
    -0.70
    fu
    -0.69
    drivers
    -0.67
    POSITIVE LOGITS
    minster
    0.81
    oppers
    0.80
    icago
    0.80
    nyder
    0.73
    onite
    0.73
    heimer
    0.71
    orius
    0.69
     Logged
    0.69
    insula
    0.69
    oint
    0.69
    Activations Density 0.081%

    No Known Activations