© 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. 9-RES-JB
    11. 1973
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving or changing the world, specifically mentioning "America Great Again"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to improving the world and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     validity
    -0.84
     omission
    -0.81
     timing
    -0.75
     clearance
    -0.73
     suggestion
    -0.68
     residues
    -0.67
     detail
    -0.64
     delay
    -0.64
     angle
    -0.64
     estimate
    -0.63
    POSITIVE LOGITS
     multicultural
    0.96
     democracies
    0.91
    heid
    0.89
     prosperous
    0.87
    govern
    0.82
     dystop
    0.81
     liv
    0.81
    iven
    0.80
     industrialized
    0.80
     prosper
    0.78
    Activations Density 0.389%

    No Known Activations