© 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. 11-RES-JB
    11. 19295
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to Egypt

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "egg."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naughty
    -0.68
    DERR
    -0.63
     Wicked
    -0.62
     fact
    -0.62
     equity
    -0.58
     Hots
    -0.58
     juxtap
    -0.56
     respons
    -0.56
     shy
    -0.56
     Whale
    -0.54
    POSITIVE LOGITS
    raphics
    1.39
    asus
    1.38
    lasses
    1.26
    roups
    1.18
    roup
    1.15
    rowth
    1.12
    regate
    1.09
    raphic
    1.08
    otiation
    1.07
    entric
    1.07
    Activations Density 0.043%

    No Known Activations