© 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. 8-RES-JB
    11. 17854
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly the name "Laura"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of specific names, particularly "Laura."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.97
    MENTS
    -0.76
    rated
    -0.76
    */(
    -0.72
    cffffcc
    -0.71
    fleet
    -0.69
     nomine
    -0.69
    nces
    -0.69
    Ü
    -0.67
    urated
    -0.67
    POSITIVE LOGITS
     Palmer
    1.08
     Jane
    1.00
     Bloom
    0.84
     Ing
    0.82
     Loren
    0.80
     Bates
    0.79
     Kate
    0.78
    Jane
    0.78
     Joy
    0.77
     Weather
    0.77
    Activations Density 0.025%

    No Known Activations