© 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. 6-RES-JB
    11. 3531
    Prev
    Next
    INDEX
    Explanations

    references to politicians, specifically related to investigations or controversies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Clinton"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.79
    GGGGGGGG
    -0.78
    lass
    -0.78
    Reviewer
    -0.70
     Gareth
    -0.70
    DIS
    -0.69
    CAST
    -0.69
    semble
    -0.69
     Flavoring
    -0.68
    orescent
    -0.68
    POSITIVE LOGITS
     Clinton
    1.05
    Clinton
    0.97
    mia
    0.90
    INTON
    0.89
     Hillary
    0.85
     impeachment
    0.83
     Supporters
    0.83
    clinton
    0.81
    ites
    0.78
    ite
    0.76
    Activations Density 0.027%

    No Known Activations