© 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. 10468
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cur" with varying contexts and spellings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cur" and its variations in different contexts

    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
    lihood
    -0.71
     Phant
    -0.71
     Stronghold
    -0.70
     Titanic
    -0.69
    ZI
    -0.69
     Opportunity
    -0.68
     Fields
    -0.67
    heit
    -0.67
     Doctrine
    -0.66
     Advance
    -0.66
    POSITIVE LOGITS
     cur
    1.07
    cur
    1.03
    bum
    1.00
    rie
    0.99
    ving
    0.97
    tailed
    0.92
    few
    0.89
    tain
    0.87
    vier
    0.87
    ricular
    0.87
    Activations Density 0.007%

    No Known Activations