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. 12359
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific Pokémon characters and attributes

    oai_token-act-pair · gpt-3.5-turbo

    specific character or symbol patterns resembling encoding or special characters

    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
    olit
    -0.85
    ithing
    -0.76
    zees
    -0.73
     pros
    -0.71
     perspect
    -0.71
    wcs
    -0.71
     Stew
    -0.71
    arton
    -0.70
    olicy
    -0.70
     kosher
    -0.70
    POSITIVE LOGITS
    ãĤ«
    1.84
    ãĥĨ
    1.78
    ãĥ©
    1.78
    ãĥ«
    1.77
    ãĥ³
    1.77
    ãĤ¯
    1.75
    ãĥ¼ãĥ³
    1.75
    ãĤ¿
    1.74
    ãĤŃ
    1.74
    ãĥª
    1.71
    Activations Density 0.015%

    No Known Activations