© 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. 12795
    Prev
    Next
    INDEX
    Explanations

    common names, specifically the name "Nick"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nick."

    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
    女
    -0.79
    ãĥ´ãĤ¡
    -0.78
     à¨
    -0.77
    ãĥĩãĤ£
    -0.75
    ASED
    -0.73
    ptives
    -0.72
    sbm
    -0.71
    20439
    -0.71
    ACTED
    -0.70
    è¦ļéĨĴ
    -0.70
    POSITIVE LOGITS
    laus
    1.17
    named
    1.06
     Nick
    1.00
    ety
    0.99
    imus
    0.98
    olas
    0.96
    Nick
    0.92
    ophon
    0.88
    erson
    0.86
     Wilde
    0.86
    Activations Density 0.007%

    No Known Activations