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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 19635
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kennedy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kennedy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ox
    -0.69
     Ae
    -0.68
     translate
    -0.67
     offline
    -0.66
    tl
    -0.63
    .—
    -0.61
    ================================================================
    -0.61
     dungeon
    -0.60
     regul
    -0.60
     mode
    -0.59
    POSITIVE LOGITS
     Kennedy
    3.81
    Kenn
    2.37
     JFK
    2.36
     Eisenhower
    1.57
     Castro
    1.52
     Kenn
    1.46
     Reagan
    1.45
     Nixon
    1.45
     Lyndon
    1.44
    FK
    1.43
    Activations Density 0.025%

    No Known Activations