© 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. 4-RES-JB
    11. 22081
    Prev
    Next
    INDEX
    Explanations

    the last name "Schultz" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names related to political and organizational figures

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

    No Comments

    Negative Logits
    ather
    -0.77
    66666666
    -0.76
    ative
    -0.72
    ãĤ¤ãĥĪ
    -0.71
    ators
    -0.70
    ãĤĮ
    -0.69
    icable
    -0.69
    IGHTS
    -0.69
    liness
    -0.68
    ativity
    -0.68
    POSITIVE LOGITS
     Schultz
    0.87
    icago
    0.83
    olicy
    0.78
    oled
    0.76
    arella
    0.74
    plin
    0.72
    unia
    0.70
     Wasserman
    0.69
    ultz
    0.68
    isine
    0.67
    Activations Density 0.021%

    No Known Activations