© 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. 4246
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Czechoslovakia

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Czechoslovakia."

    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
     mosqu
    -0.83
     eleph
    -0.69
    ¥ŀ
    -0.68
    Orderable
    -0.67
    ermott
    -0.67
    ĸļ士
    -0.66
     bailed
    -0.65
     metic
    -0.64
    onet
    -0.64
    querque
    -0.62
    POSITIVE LOGITS
    oslov
    0.98
    ners
    0.95
    liness
    0.89
    ski
    0.85
    heid
    0.84
    lav
    0.83
    ner
    0.81
    chn
    0.81
    icular
    0.80
    chen
    0.79
    Activations Density 0.028%

    No Known Activations