© 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. 24297
    Prev
    Next
    INDEX
    Explanations

    references to Paganism and its historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to Pagan beliefs or culture

    oai_token-act-pair · gpt-3.5-turbo
    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
    hirt
    -0.72
    wards
    -0.72
    cream
    -0.67
     Bever
    -0.66
    ĨĴ
    -0.65
     Nicotine
    -0.65
    demand
    -0.65
    CLA
    -0.65
    shock
    -0.64
     Contrast
    -0.63
    POSITIVE LOGITS
     Pag
    1.34
    antry
    1.06
    agate
    1.01
     pag
    0.96
    osa
    0.95
    atis
    0.90
    asus
    0.88
    asa
    0.87
    asonry
    0.85
    asin
    0.84
    Activations Density 0.008%

    No Known Activations