© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10665
    Prev
    Next
    INDEX
    Explanations

    phrases related to political investigations and appointments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political allegations and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.77
    vier
    -0.77
    !--
    -0.72
    theless
    -0.64
    prises
    -0.63
     VIDEOS
    -0.59
    umbered
    -0.57
     "$:/
    -0.57
    haps
    -0.57
    webkit
    -0.56
    POSITIVE LOGITS
     Rosenstein
    0.71
    ghazi
    0.65
     Kavanaugh
    0.64
     dossier
    0.60
    ctuary
    0.60
     Mueller
    0.58
    vernight
    0.58
     Kislyak
    0.58
    FBI
    0.56
     Oval
    0.56
    Activations Density 0.018%

    No Known Activations