© 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. 15167
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or global affairs

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term 'affairs' in various contexts

    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
    ingham
    -0.75
    oug
    -0.70
    åĭ
    -0.67
    asel
    -0.65
    ammy
    -0.64
    bern
    -0.64
    DIT
    -0.63
    yrics
    -0.63
    liam
    -0.62
    DES
    -0.62
    POSITIVE LOGITS
     affairs
    1.35
     Affairs
    0.83
    afety
    0.81
    itaire
    0.78
    ername
    0.74
     Adviser
    0.73
    etter
    0.72
    hip
    0.72
     Matters
    0.71
    olitics
    0.71
    Activations Density 0.005%

    No Known Activations