© 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. 9-RES-JB
    11. 4200
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discourse and the balance between security and liberty

    oai_token-act-pair · gpt-3.5-turbo

    themes related to accountability and the consequences of actions in society

    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
     ..."
    -0.78
    [/
    -0.72
    Enlarge
    -0.69
    assium
    -0.67
     \"
    -0.67
     Basically
    -0.66
    Basically
    -0.66
    ..."
    -0.66
    ''
    -0.66
     Paddock
    -0.65
    POSITIVE LOGITS
     principled
    0.97
     complicit
    0.95
     democratically
    0.95
     acquies
    0.94
     complicity
    0.94
     democracies
    0.94
     impover
    0.91
     democratic
    0.90
     progressives
    0.90
     emanc
    0.87
    Activations Density 1.454%

    No Known Activations