© 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. 4-RES-JB
    11. 7555
    Prev
    Next
    INDEX
    Explanations

    proper names containing the specific syllable "lav"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lav" and its variations, indicating a focus on a specific individual or brand

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

    No Comments

    Negative Logits
    PDATE
    -0.76
    roads
    -0.69
    Ĥª
    -0.69
    PRES
    -0.69
    WER
    -0.66
     Palin
    -0.66
    manship
    -0.66
    figure
    -0.64
     Reaper
    -0.64
     mouse
    -0.62
    POSITIVE LOGITS
     Lav
    1.16
    iolet
    1.14
    ishly
    1.03
    ita
    0.94
    igne
    0.93
    atories
    0.93
    aca
    0.92
    acy
    0.91
    onte
    0.91
    endar
    0.90
    Activations Density 0.010%

    No Known Activations