© 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. 11-RES-JB
    11. 14914
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and political commentary

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social and political discourse, particularly around issues of oppression and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Talks
    -0.82
     doesnt
    -0.79
     10000
    -0.77
    OTOS
    -0.76
     TN
    -0.75
     Saying
    -0.75
    ï¸ı
    -0.74
    Delivery
    -0.73
     Finish
    -0.73
     Didn
    -0.72
    POSITIVE LOGITS
     metast
    1.37
     perme
    1.30
     coales
    1.26
     corro
    1.26
     prolifer
    1.21
     suppl
    1.18
     embold
    1.13
     intersect
    1.09
     legitim
    1.08
     resurg
    1.08
    Activations Density 0.408%

    No Known Activations