© 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. 12103
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement activities

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     rank
    -0.69
     prelim
    -0.67
     battles
    -0.66
     heck
    -0.64
     hust
    -0.64
    board
    -0.64
     hero
    -0.63
     spar
    -0.62
     cook
    -0.61
     parap
    -0.61
    POSITIVE LOGITS
    AAA
    0.85
    Excellent
    0.83
    nai
    0.82
    moderate
    0.81
    catentry
    0.81
    ...]
    0.81
    Our
    0.79
    We
    0.79
    Virgin
    0.77
    BuyableInstoreAndOnline
    0.77
    Activations Density 0.060%

    No Known Activations