© 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. 10-RES-JB
    11. 8338
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or official statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statements and allegations in a political context

    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
     occasionally
    -0.72
     depending
    -0.71
    Interstitial
    -0.70
     specialize
    -0.69
     somet
    -0.69
    pmwiki
    -0.68
     whenever
    -0.67
    ulton
    -0.67
     periodically
    -0.67
     situations
    -0.66
    POSITIVE LOGITS
     Lavrov
    0.89
     Flynn
    0.81
     Tillerson
    0.79
     Cohn
    0.78
     Sessions
    0.78
     Ms
    0.78
     MH
    0.76
     Harvey
    0.76
     Pruitt
    0.75
     Garland
    0.75
    Activations Density 0.428%

    No Known Activations