© 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. 1-RES-JB
    11. 3882
    Prev
    Next
    INDEX
    Explanations

    references to the name "Follett" or potential variations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or a character named "Fol."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SUP
    -0.68
    LESS
    -0.62
    pocket
    -0.61
     hawk
    -0.61
    shapeshifter
    -0.60
     ASC
    -0.60
     chained
    -0.59
    eer
    -0.58
    ARK
    -0.58
    ONS
    -0.57
    POSITIVE LOGITS
     Fol
    1.06
     unden
    0.98
    ername
    0.87
    ilial
    0.86
    lette
    0.84
    terness
    0.84
    atility
    0.80
    phies
    0.80
    itaire
    0.80
    iage
    0.79
    Activations Density 0.005%

    No Known Activations