© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6737
    Prev
    Next
    INDEX
    Explanations

    mentions of people in leadership positions, specifically chairmen

    oai_token-act-pair · gpt-3.5-turbo

    the term "chairman" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    uder
    -0.76
    tnc
    -0.73
    emp
    -0.72
    asca
    -0.71
    اÙĦ
    -0.70
     Siber
    -0.70
    aver
    -0.69
    ENC
    -0.67
    veh
    -0.65
    1000
    -0.64
    POSITIVE LOGITS
     chairman
    1.23
    ority
    1.00
     Chairman
    0.98
     chair
    0.92
    Chair
    0.85
    IAL
    0.84
    chair
    0.83
    pins
    0.80
    woman
    0.79
    swer
    0.77
    Activations Density 0.008%

    No Known Activations