© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20042
    Prev
    Next
    INDEX
    Explanations

    derogatory language or remarks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to racial slurs and derogatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    compan
    -0.70
    session
    -0.68
    angel
    -0.66
    NetMessage
    -0.62
    ocr
    -0.61
    growth
    -0.61
     reconc
    -0.61
    packing
    -0.61
     Folder
    -0.61
    Whe
    -0.60
    POSITIVE LOGITS
     slurs
    1.43
     slur
    1.24
    pees
    0.80
    plings
    0.80
    rimination
    0.78
     dispar
    0.76
    iple
    0.74
    ï¸ı
    0.73
     guiActiveUn
    0.72
     insults
    0.71
    Activations Density 0.013%

    No Known Activations