© 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. 479
    Prev
    Next
    INDEX
    Explanations

    words related to strong feelings of shock or disapproval

    oai_token-act-pair · gpt-4-turbo

    phrases or words related to public outrage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outrage" and its contextual implications

    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
    ramid
    -0.71
    ramer
    -0.71
     Solitaire
    -0.69
    âĢ¢âĢ¢
    -0.68
    NetMessage
    -0.67
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.66
    aah
    -0.66
    stood
    -0.66
    uchin
    -0.66
    essions
    -0.65
    POSITIVE LOGITS
    ously
    1.06
     indignation
    1.05
     outrage
    0.90
    iously
    0.87
     uproar
    0.86
    urous
    0.78
     outcry
    0.77
    bolt
    0.74
    ati
    0.72
    uously
    0.70
    Activations Density 0.011%

    No Known Activations