© 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. 3-RES-JB
    11. 23002
    Prev
    Next
    INDEX
    Explanations

    the name "Stanton" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Stanton" and its variations in the context of sports and legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -1.35
    ĨĴ
    -0.80
    ¥ŀ
    -0.76
    ļéĨĴ
    -0.75
    tops
    -0.73
    oan
    -0.70
    umen
    -0.69
    ternity
    -0.69
    oos
    -0.68
    ŀ
    -0.66
    POSITIVE LOGITS
     Stras
    0.94
    OPLE
    0.90
     Stanton
    0.82
    acco
    0.82
     STL
    0.78
    ampton
    0.68
     RHP
    0.67
    bug
    0.66
    ASED
    0.66
    chers
    0.66
    Activations Density 0.017%

    No Known Activations