© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13380
    Prev
    Next
    INDEX
    Explanations

    pertaining to a specific person named Mezvinsky, potentially with a political or personal context

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Mezvinsky

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meet
    -0.76
    ãĥ¼ãĥ³
    -0.75
    worldly
    -0.66
    Joined
    -0.62
    chal
    -0.62
     vested
    -0.61
     lesser
    -0.61
    matched
    -0.61
    seeing
    -0.61
    lessness
    -0.60
    POSITIVE LOGITS
    insky
    1.20
    akov
    0.89
    loo
    0.86
    arella
    0.83
    hattan
    0.81
    issance
    0.78
    qi
    0.77
    inski
    0.77
    gren
    0.77
    berg
    0.75
    Activations Density 0.010%

    No Known Activations