© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6623
    Prev
    Next
    INDEX
    Explanations

    references to someone's first appearance or the first instance of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "debut."

    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
    akia
    -0.71
    bara
    -0.70
    nc
    -0.65
     Canaver
    -0.65
    learn
    -0.63
    apons
    -0.63
    chn
    -0.62
     annexed
    -0.62
    ombs
    -0.61
    par
    -0.60
    POSITIVE LOGITS
    antes
    1.06
    ante
    0.94
    antly
    0.83
    interstitial
    0.79
    iator
    0.78
     debut
    0.77
    iating
    0.76
    ãĥ¼ãĥĨãĤ£
    0.73
    iour
    0.73
    iates
    0.69
    Activations Density 0.019%

    No Known Activations