© 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. 1-RES-JB
    11. 21090
    Prev
    Next
    INDEX
    Explanations

    terms related to holiness or containing the string "hol"

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts related to "holism" and specific terms starting with "hol."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EED
    -0.66
    REE
    -0.66
     approve
    -0.65
    Magikarp
    -0.64
     Abyssal
    -0.64
    anova
    -0.62
    INS
    -0.62
    aeda
    -0.62
     Eag
    -0.61
    Interstitial
    -0.61
    POSITIVE LOGITS
    ocaust
    1.39
     hol
    1.23
    iday
    1.03
    icho
    0.89
    istically
    0.88
    onomic
    0.83
    idays
    0.81
    olith
    0.79
    ophon
    0.78
    osc
    0.76
    Activations Density 0.007%

    No Known Activations