© 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. 1-RES-JB
    11. 19983
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and socioeconomic aspects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geography and socio-economic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.82
    owship
    -0.81
     Curve
    -0.80
    shall
    -0.78
     Granger
    -0.76
    uously
    -0.75
    uous
    -0.74
    ians
    -0.72
    amental
    -0.72
    ance
    -0.71
    POSITIVE LOGITS
     geo
    0.93
    hazard
    0.88
     versa
    0.87
    econom
    0.86
    ffe
    0.84
    occup
    0.82
    fit
    0.82
    jo
    0.82
    hab
    0.82
    xon
    0.81
    Activations Density 0.016%

    No Known Activations