© 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. 2-RES-JB
    11. 341
    Prev
    Next
    INDEX
    Explanations

    the word "chairman"

    oai_token-act-pair · gpt-4-turbo

    proper nouns, specifically names of chairmen

    oai_token-act-pair · gpt-3.5-turbo

    references to positions of authority, specifically those of chairpersons or chairmen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uder
    -0.75
    asca
    -0.74
    اÙĦ
    -0.69
    aver
    -0.68
    ENC
    -0.68
     Siber
    -0.67
    emp
    -0.65
    VK
    -0.64
     southwestern
    -0.63
    Sharp
    -0.61
    POSITIVE LOGITS
     chairman
    1.05
    ority
    0.97
     Chairman
    0.91
    IAL
    0.90
     chair
    0.86
    doms
    0.78
    chair
    0.76
    woman
    0.74
     rabbi
    0.74
    pins
    0.73
    Activations Density 0.011%

    No Known Activations