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. 14352
    Prev
    Next
    INDEX
    Explanations

    the name "Ben Affleck"

    oai_token-act-pair · gpt-3.5-turbo

    references to the actor Ben Affleck

    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
     North
    -0.69
     exp
    -0.67
     spirits
    -0.66
     tab
    -0.66
     IC
    -0.65
     virtual
    -0.63
     Native
    -0.63
     Odyssey
    -0.63
     mult
    -0.63
     PRO
    -0.63
    POSITIVE LOGITS
    leck
    5.39
    lest
    1.08
    hoff
    1.06
    loe
    1.01
    wagen
    0.99
    lus
    0.97
    tsky
    0.96
    lett
    0.94
    cki
    0.94
    anski
    0.93
    Activations Density 0.021%

    No Known Activations