Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21178
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent events and their aftermath

    oai_token-act-pair · gpt-3.5-turbo

    references to mass shooting events and their associated statistics

    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
    OGR
    -0.77
    rils
    -0.68
    FIX
    -0.67
     deficiency
    -0.67
    ernels
    -0.67
    Dial
    -0.66
    verb
    -0.65
    cro
    -0.64
    oval
    -0.64
    ripp
    -0.64
    POSITIVE LOGITS
     Sikh
    1.07
     nightclub
    1.06
     crowded
    0.99
     satirical
    0.99
     kosher
    0.98
     synagogue
    0.97
     concert
    0.95
     commuter
    0.93
     Pulse
    0.90
     Christmas
    0.86
    Activations Density 0.177%

    No Known Activations