© 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. 20665
    Prev
    Next
    INDEX
    Explanations

    information related to human rights violations and political oppression

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with state-sponsored violence and arbitrary actions against communities

    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
    IENCE
    -0.81
     Remastered
    -0.78
    phies
    -0.72
     Horizons
    -0.72
     partName
    -0.71
     Frie
    -0.70
    nect
    -0.70
    ftime
    -0.69
    topic
    -0.69
    uscript
    -0.67
    POSITIVE LOGITS
     repression
    1.45
     repressive
    1.44
     confisc
    1.41
     persecut
    1.39
     imprison
    1.35
     unconstitutional
    1.31
     arbitrary
    1.30
     draconian
    1.29
     coercive
    1.27
     coerc
    1.25
    Activations Density 0.777%

    No Known Activations