© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18542
    Prev
    Next
    INDEX
    Explanations

    references to the assassination of JFK and related individuals and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the JFK assassination and related figures

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

    No Comments

    Negative Logits
     Flavoring
    -0.83
    verbs
    -0.72
    Downloadha
    -0.72
    Greek
    -0.70
    ×ij
    -0.68
    Ire
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    È
    -0.67
    Natural
    -0.65
    ãĥł
    -0.65
    POSITIVE LOGITS
     Assass
    1.18
     JFK
    1.18
     Oswald
    1.01
     Kennedy
    0.99
     assassination
    0.99
     Presidential
    0.84
    eering
    0.82
     Lyndon
    0.76
     assassinated
    0.74
     assassin
    0.72
    Activations Density 0.013%

    No Known Activations