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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 324
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sou" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sou" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kirin
    -0.66
     Pax
    -0.65
    OY
    -0.62
     Goth
    -0.58
     boundaries
    -0.58
     misinformation
    -0.58
     Triangle
    -0.58
    oded
    -0.57
    utic
    -0.57
     Warsaw
    -0.56
    POSITIVE LOGITS
    cery
    1.20
    ven
    1.14
    quet
    1.05
    velt
    1.04
    gue
    1.03
    reth
    1.02
    lette
    1.01
    llo
    0.99
    chet
    0.99
    phony
    0.98
    Activations Density 0.037%

    No Known Activations