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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 10-RES-JB
    6. 7723
    Prev
    Next
    INDEX
    Explanations

    references to the name "Kennedy."

    oai_token-act-pair · gpt-3.5-turbo

    references to John F. Kennedy and related historical events, particularly the assassination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resp
    -0.74
    places
    -0.69
    putable
    -0.69
    tery
    -0.69
    odcast
    -0.69
    Ö¼
    -0.69
    Greek
    -0.69
    tics
    -0.68
    cipl
    -0.66
    tml
    -0.65
    POSITIVE LOGITS
     Assass
    1.13
     assassination
    0.96
     Kennedy
    0.93
    ega
    0.78
    LM
    0.75
    emouth
    0.74
     Oswald
    0.73
     Jr
    0.71
     Shuttle
    0.69
    esque
    0.69
    Activations Density 0.037%

    No Known Activations