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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3861
    Prev
    Next
    INDEX
    Explanations

    legal and historical terms, particularly related to civil rights and legal rights

    oai_token-act-pair · gpt-3.5-turbo

    references to civil rights issues and historical injustices

    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
     GoPro
    -1.02
     Ãĸ
    -0.96
     Nex
    -0.93
     Dota
    -0.90
    Meta
    -0.86
     Xiaomi
    -0.86
    Magikarp
    -0.85
     iT
    -0.85
     Pikachu
    -0.84
     AoE
    -0.83
    POSITIVE LOGITS
     Negro
    2.02
     slavery
    1.91
     slave
    1.79
     Confederate
    1.78
     slaves
    1.76
     segregation
    1.76
     Confederacy
    1.73
     plantation
    1.71
     blacks
    1.69
     negro
    1.68
    Activations Density 0.426%

    No Known Activations