© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16995
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Pil" alongside some other occurrences that aren't directly related to each other

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Pil" in various contexts

    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
    anwhile
    -0.90
     EntityItem
    -0.79
     Carbuncle
    -0.73
    hips
    -0.69
     Satanic
    -0.66
    lies
    -0.65
     Baird
    -0.63
     Clapper
    -0.62
     Beir
    -0.61
    ires
    -0.61
    POSITIVE LOGITS
    oted
    1.01
    crow
    0.98
    wings
    0.97
    chard
    0.93
    awar
    0.89
    cipled
    0.86
    ando
    0.84
    iqu
    0.84
    cone
    0.83
    cy
    0.82
    Activations Density 0.012%

    No Known Activations