© 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. 4-RES-JB
    11. 1001
    Prev
    Next
    INDEX
    Explanations

    verbs related to defending or justifying actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of people defending or criticizing others

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

    No Comments

    Negative Logits
    ctors
    -0.73
    AMY
    -0.68
    soDeliveryDate
    -0.68
    GROUP
    -0.65
     Certificate
    -0.62
    ccess
    -0.62
     computation
    -0.61
    ordering
    -0.61
    esc
    -0.60
    window
    -0.59
    POSITIVE LOGITS
     angrily
    0.79
     vehemently
    0.75
     blasting
    0.74
     softened
    0.72
     sarcast
    0.70
     passionately
    0.69
     bluntly
    0.69
     forcefully
    0.69
     criticisms
    0.68
     aired
    0.68
    Activations Density 0.613%

    No Known Activations