© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24299
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "condemn" and its variations related to denouncing actions or events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    emis
    -0.81
    ramid
    -0.75
    lio
    -0.75
    neau
    -0.73
    BLIC
    -0.72
    IER
    -0.71
    soDeliveryDate
    -0.70
    uana
    -0.70
    Ranked
    -0.69
    OTE
    -0.67
    POSITIVE LOGITS
     racism
    0.93
     atrocities
    0.91
     violence
    0.90
     hypocrisy
    0.87
     vandalism
    0.86
     actions
    0.85
     homophobic
    0.85
     condemn
    0.83
     abuses
    0.82
     unequivocally
    0.81
    Activations Density 0.076%

    No Known Activations