© 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. 7-RES-JB
    11. 20878
    Prev
    Next
    INDEX
    Explanations

    phrases discussing economic and political issues

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or estimates related to political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upstairs
    -0.75
     downstairs
    -0.71
    iton
    -0.69
     amph
    -0.67
     attent
    -0.65
     Pag
    -0.63
     Osc
    -0.63
     scram
    -0.62
     inactive
    -0.62
     Creed
    -0.61
    POSITIVE LOGITS
    Econom
    1.10
    ³³³³³³³³
    1.09
    ³³³³
    0.96
    ³³³³³³³³³³³³³³³³
    0.92
    ³³³
    0.91
    Economic
    0.86
    Therefore
    0.81
    Posted
    0.79
    ccording
    0.78
    Population
    0.78
    Activations Density 0.443%

    No Known Activations