© 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. 1-RES-JB
    11. 3607
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical figures or celebrities

    oai_token-act-pair · gpt-3.5-turbo

    names of historical figures, particularly those with the surname "Franz" or related to "Ferdinand"

    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
    ilk
    -1.01
    apers
    -0.80
    asin
    -0.78
    aping
    -0.74
    aped
    -0.69
    ©¶æ
    -0.68
    EEK
    -0.68
    ç¥ŀ
    -0.67
    pora
    -0.67
    OUT
    -0.67
    POSITIVE LOGITS
    dinand
    1.56
     Ferdinand
    1.26
    sson
    1.12
    swer
    0.99
    lication
    0.90
     Ludwig
    0.89
     Friedrich
    0.89
     Ernst
    0.89
     Gustav
    0.85
    furt
    0.83
    Activations Density 0.010%

    No Known Activations