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. 1-RES-JB
    6. 2879
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named Kejriwal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Kejriwal and Keynes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onial
    -0.85
    heon
    -0.84
    heast
    -0.83
    namese
    -0.82
    encers
    -0.81
    rals
    -0.78
    urity
    -0.76
    orious
    -0.76
    rified
    -0.75
    anamo
    -0.72
    POSITIVE LOGITS
    jriwal
    1.51
     Kejriwal
    1.19
    Ke
    0.87
    zeb
    0.75
    TPPStreamerBot
    0.73
    Desk
    0.73
    ji
    0.72
    haw
    0.72
     Keynes
    0.69
    ItemImage
    0.68
    Activations Density 0.007%

    No Known Activations