© 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. 6-RES-JB
    11. 13737
    Prev
    Next
    INDEX
    Explanations

    references to the Kennedy family

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Kennedy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.76
    resp
    -0.75
    ãĤ¯
    -0.74
    icult
    -0.73
    putable
    -0.72
    mental
    -0.71
    Greek
    -0.70
     Flavoring
    -0.70
    ages
    -0.69
    regulated
    -0.67
    POSITIVE LOGITS
     Assass
    1.05
     Kennedy
    1.03
     assassination
    0.90
    esque
    0.77
    istic
    0.74
    ega
    0.73
    istically
    0.70
     Landing
    0.69
     Emanuel
    0.68
    LM
    0.67
    Activations Density 0.022%

    No Known Activations