© 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. 10-RES-JB
    11. 3417
    Prev
    Next
    INDEX
    Explanations

    mentions of political alliances and support between countries or factions

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events involving the Nazi regime and related political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agogue
    -0.71
    cloth
    -0.69
    ando
    -0.68
    anish
    -0.67
    CNN
    -0.65
    ographers
    -0.65
    rians
    -0.64
     arsen
    -0.64
    ographer
    -0.63
    agnetic
    -0.62
    POSITIVE LOGITS
     elections
    0.85
     emergencies
    0.81
     negotiations
    0.80
     drafting
    0.79
     relocation
    0.78
     dealings
    0.76
     sponsoring
    0.76
     organising
    0.75
     Tours
    0.74
     administering
    0.74
    Activations Density 0.315%

    No Known Activations