© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15121
    Prev
    Next
    INDEX
    Explanations

    mentions of national entities

    oai_token-act-pair · gpt-3.5-turbo

    references to national issues or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lov
    -0.77
    ester
    -0.73
    comed
    -0.70
    rete
    -0.68
     wherein
    -0.68
     [&
    -0.67
    block
    -0.67
    tenance
    -0.65
    roller
    -0.64
    SCP
    -0.64
    POSITIVE LOGITS
     national
    3.57
    national
    2.54
    National
    2.33
     National
    2.19
     nationally
    1.89
     nationwide
    1.72
     nation
    1.70
     statewide
    1.66
     regional
    1.61
     nationals
    1.54
    Activations Density 0.021%

    No Known Activations