© 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. 16457
    Prev
    Next
    INDEX
    Explanations

    locations related to significant tragic events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant tragic events and locations

    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
    veland
    -0.83
    olson
    -0.76
    ucha
    -0.73
    istant
    -0.73
    mson
    -0.71
    atively
    -0.70
    uria
    -0.70
    wine
    -0.69
    jun
    -0.68
    utical
    -0.68
    POSITIVE LOGITS
     Massacre
    1.34
     massacre
    1.17
     tragedy
    1.00
     victims
    1.00
     survivors
    0.97
     massacres
    0.97
     disaster
    0.96
     shootings
    0.96
     Incident
    0.95
     catastrophe
    0.95
    Activations Density 0.177%

    No Known Activations