© 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. 10-RES-JB
    11. 10585
    Prev
    Next
    INDEX
    Explanations

    terms or phrases with the letter "F" as the key component

    oai_token-act-pair · gpt-3.5-turbo

    the letter "F" at the beginning of words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patriarch
    -0.66
     lapse
    -0.62
     Pharaoh
    -0.62
     Mellon
    -0.62
     fringe
    -0.61
     mater
    -0.61
     hosts
    -0.61
     machine
    -0.60
     Journals
    -0.60
     Gab
    -0.60
    POSITIVE LOGITS
    requently
    1.39
    rozen
    1.37
    requency
    1.35
    erguson
    1.32
    antasy
    1.30
    ellow
    1.27
    ALSE
    1.27
    ernand
    1.27
    ederation
    1.26
    amous
    1.26
    Activations Density 0.037%

    No Known Activations