© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22212
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political conflicts or struggles

    oai_token-act-pair · gpt-3.5-turbo

    language related to oppression and social justice issues

    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
    earch
    -0.70
    bridge
    -0.67
    00200000
    -0.66
    ãĥĩãĤ£
    -0.65
    2020
    -0.64
    ++)
    -0.63
    âĦ¢:
    -0.63
    ilot
    -0.62
    éĹĺ
    -0.62
    tto
    -0.61
    POSITIVE LOGITS
     oppress
    1.40
     oppressive
    1.29
     patriarchy
    1.21
     tyrann
    1.16
     capitalist
    1.14
     tyranny
    1.14
     patriarchal
    1.13
     rulers
    1.13
     tyrant
    1.10
     repressive
    1.08
    Activations Density 0.547%

    No Known Activations