© 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. 10262
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of violent incidents or serious 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
     Tsukuyomi
    -0.78
    Newsletter
    -0.77
     Izan
    -0.76
     Trees
    -0.71
    ';
    -0.70
     Seller
    -0.68
     Mig
    -0.65
    éĹĺ
    -0.65
    ];
    -0.64
     Vader
    -0.64
    POSITIVE LOGITS
    dinand
    0.72
     embattled
    0.72
    attled
    0.67
     superf
    0.61
     concess
    0.61
     nomine
    0.61
     naughty
    0.60
     controversial
    0.60
     elusive
    0.59
    UST
    0.58
    Activations Density 1.637%

    No Known Activations