© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "checking"

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of checking or verifying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pire
    -0.72
     Ribbon
    -0.71
    ocry
    -0.67
    thora
    -0.67
    JV
    -0.64
     epit
    -0.62
    ras
    -0.61
    ustain
    -0.60
    aqu
    -0.60
    NRS
    -0.59
    POSITIVE LOGITS
     checking
    3.56
    checking
    2.60
     Checking
    2.53
     check
    2.11
     checks
    2.05
     checked
    1.92
    check
    1.86
     verifying
    1.75
    checks
    1.73
    Check
    1.70
    Activations Density 0.009%

    No Known Activations