© 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. 23740
    Prev
    Next
    INDEX
    Explanations

    social media sharing and subscription-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to email and newsletters

    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
     Kad
    -0.61
     Knife
    -0.60
    ãĥķãĤ¡
    -0.60
     Catalyst
    -0.59
    ono
    -0.59
    pent
    -0.58
     mole
    -0.57
     Sof
    -0.56
    Mas
    -0.55
    paces
    -0.55
    POSITIVE LOGITS
     Cancel
    0.67
    interstitial
    0.61
     captcha
    0.58
     Treasurer
    0.58
    Interstitial
    0.57
    reau
    0.57
    yright
    0.56
    ername
    0.56
    omever
    0.55
    entimes
    0.54
    Activations Density 0.063%

    No Known Activations