© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 10026
    Prev
    Next
    INDEX
    Explanations

    words related to political figures, particularly Hillary Clinton and Bernie Sanders

    oai_token-act-pair · gpt-3.5-turbo

    quotes and statements made by political figures

    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
    pmwiki
    -0.83
     largeDownload
    -0.82
    âĹ¼
    -0.76
     CrossRef
    -0.72
    estones
    -0.70
    ruary
    -0.68
    Thumbnail
    -0.68
     Lans
    -0.67
    acl
    -0.67
    cific
    -0.66
    POSITIVE LOGITS
    ħ
    0.71
     Kavanaugh
    0.70
    ¿
    0.68
    Ħ¢
    0.63
     believable
    0.62
     allegation
    0.60
    ']
    0.58
     probe
    0.57
    '/
    0.56
     Dems
    0.56
    Activations Density 0.047%

    No Known Activations