© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5506
    Prev
    Next
    INDEX
    Explanations

    phrases or documents containing the word "critical."

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism directed at individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
     Masquerade
    -0.70
    ItemImage
    -0.69
     gasp
    -0.69
     anticipation
    -0.67
    MX
    -0.66
    ultane
    -0.63
    daq
    -0.63
    MAP
    -0.63
     saliva
    -0.62
    POSITIVE LOGITS
     sorts
    0.74
     homosexuality
    0.72
     capitalism
    0.69
     perceived
    0.68
     course
    0.66
     communism
    0.66
    social
    0.65
     prevailing
    0.65
     harshly
    0.65
     bigotry
    0.63
    Activations Density 0.103%

    No Known Activations