© 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. 14557
    Prev
    Next
    INDEX
    Explanations

    keywords related to markets and industries

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to markets, media, and military or strategic concepts

    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
    heart
    -0.68
    KEY
    -0.67
    pac
    -0.66
    Nap
    -0.62
    irlf
    -0.62
    risk
    -0.61
    pu
    -0.60
    APS
    -0.60
    invest
    -0.59
    ONEY
    -0.59
    POSITIVE LOGITS
    tenance
    0.91
    llor
    0.83
    osterone
    0.78
    riors
    0.76
    ificate
    0.76
    terday
    0.74
    lihood
    0.73
     Manga
    0.70
     Stores
    0.69
    theless
    0.69
    Activations Density 0.326%

    No Known Activations