© 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. 7930
    Prev
    Next
    INDEX
    Explanations

    names of toys or characters often associated with children

    oai_token-act-pair · gpt-3.5-turbo

    words with the suffix "-y", particularly related to names or cute descriptors

    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
    itures
    -1.06
    isal
    -1.00
    aic
    -0.96
    inen
    -0.95
    iture
    -0.92
    irtual
    -0.91
    egal
    -0.89
    aution
    -0.88
    inem
    -0.87
    ormal
    -0.87
    POSITIVE LOGITS
     Bunny
    1.05
    Bee
    1.03
     Bear
    1.02
    bear
    1.02
     Doodle
    0.99
     Dee
    0.98
     Pie
    0.94
     Girl
    0.93
    bee
    0.92
     Pig
    0.91
    Activations Density 0.159%

    No Known Activations