© 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. 8-RES-JB
    11. 8501
    Prev
    Next
    INDEX
    Explanations

    phrases related to crimes and violence against individuals or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to violence against women and humanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.91
    hower
    -0.88
    daq
    -0.84
    uyomi
    -0.81
    âķIJ
    -0.76
    inventoryQuantity
    -0.71
    chall
    -0.71
     helicop
    -0.69
    ounter
    -0.68
     upd
    -0.67
    POSITIVE LOGITS
     civilians
    1.15
     minorities
    1.07
     women
    1.06
     innocent
    1.06
     females
    1.03
     Asians
    1.01
     gays
    1.00
     minors
    0.99
     homosexuals
    0.98
     Muslims
    0.95
    Activations Density 0.135%

    No Known Activations