© 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. 8-RES-JB
    11. 3329
    Prev
    Next
    INDEX
    Explanations

    terms related to political scandals and actions, specifically potentially impeachable offenses

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "impeach" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.64
    698
    -0.60
    finding
    -0.58
    utsche
    -0.58
     decom
    -0.56
     Frey
    -0.56
     Ket
    -0.55
    nesday
    -0.55
     kernels
    -0.55
     Airl
    -0.54
    POSITIVE LOGITS
    achment
    0.85
    igious
    0.75
    ãĥĥãĥĪ
    0.74
    inary
    0.73
    cientious
    0.72
    ãĥ¼ãĤ¯
    0.71
    uments
    0.70
    acers
    0.69
    lycer
    0.66
    acl
    0.65
    Activations Density 0.067%

    No Known Activations