© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 440
    Prev
    Next
    INDEX
    Explanations

    the word "criticism."

    oai_token-act-pair · gpt-4-turbo

    criticisms and negative feedback in texts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "criticism."

    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
    cise
    -0.71
    pared
    -0.67
    cop
    -0.64
    tre
    -0.64
    ibur
    -0.64
    frey
    -0.63
    change
    -0.63
    seed
    -0.63
    ramid
    -0.63
    tein
    -0.63
    POSITIVE LOGITS
     criticism
    1.00
    代
    0.96
     critic
    0.93
     criticisms
    0.86
     critics
    0.86
     Crit
    0.83
     criticizing
    0.79
     reviewers
    0.78
    imaru
    0.78
     leveled
    0.76
    Activations Density 0.021%

    No Known Activations