© 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. 2-RES-JB
    11. 551
    Prev
    Next
    INDEX
    Explanations

    words ending with "-leaning" used to describe political orientations

    oai_token-act-pair · gpt-4-turbo

    references to political leaning or alignment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political affiliations and biases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cel
    -0.81
    cial
    -0.77
    iph
    -0.75
    cell
    -0.73
    umm
    -0.73
    ICO
    -0.73
    abe
    -0.72
    izable
    -0.72
    formance
    -0.72
    abad
    -0.72
    POSITIVE LOGITS
     leaning
    1.06
     bias
    0.76
     leans
    0.76
     lean
    0.75
     skewed
    0.75
    ©¶æ
    0.74
    leaning
    0.73
     ancest
    0.73
     favoring
    0.73
     toward
    0.73
    Activations Density 0.004%

    No Known Activations