© 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. 16297
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "criticized."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "criticized."

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.73
    seed
    -0.71
    ibur
    -0.68
    ammy
    -0.66
    cession
    -0.64
    ahon
    -0.62
     occupancy
    -0.62
    ther
    -0.61
    entry
    -0.61
    nown
    -0.61
    POSITIVE LOGITS
     criticized
    1.00
     criticised
    0.92
     criticizing
    0.92
     critic
    0.87
     criticism
    0.85
     harshly
    0.82
     criticisms
    0.81
    代
    0.81
     critiques
    0.80
    imaru
    0.79
    Activations Density 0.021%

    No Known Activations