© 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. 9-RES-JB
    11. 15963
    Prev
    Next
    INDEX
    Explanations

    topics related to political issues, investigations, and reforms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to investigations and political issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    AUT
    -0.78
    Studio
    -0.76
    uci
    -0.72
     "$:/
    -0.71
    Size
    -0.71
    jac
    -0.70
    icrobial
    -0.68
     Athletic
    -0.67
    pmwiki
    -0.67
    ij士
    -0.66
    POSITIVE LOGITS
     controversy
    0.84
     debacle
    0.79
     plag
    0.75
     controversies
    0.73
     crusade
    0.71
     repeal
    0.71
     championed
    0.70
     fiasco
    0.70
     rhetoric
    0.69
     merits
    0.68
    Activations Density 0.399%

    No Known Activations