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. 3-RES-JB
    6. 7668
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual - Jared Kushner - along with locations associated with him

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kushner" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitu
    -0.86
    Ķ
    -0.74
     mindless
    -0.74
    cknowled
    -0.71
    ¡
    -0.69
    raged
    -0.63
     cac
    -0.61
    phis
    -0.59
    ++++++++++++++++
    -0.59
    usterity
    -0.58
    POSITIVE LOGITS
     Kushner
    1.04
    doms
    0.91
    gren
    0.83
    arov
    0.83
     Jinping
    0.77
    andowski
    0.76
    pai
    0.76
    icter
    0.75
    loo
    0.75
    ski
    0.72
    Activations Density 0.005%

    No Known Activations