Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6991
    Prev
    Next
    INDEX
    Explanations

    social or community-oriented messages and prompts in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    transactional phrases and requests for reader engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bras
    -0.72
    uga
    -0.71
    Ħ¢
    -0.67
    into
    -0.63
    cia
    -0.62
    ãģ®éŃĶ
    -0.61
    senal
    -0.61
    Knight
    -0.60
    oba
    -0.60
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
    POSITIVE LOGITS
    NetMessage
    0.69
    hing
    0.65
    itudes
    0.63
    level
    0.62
     LEVEL
    0.61
    turn
    0.61
     Totem
    0.60
    tor
    0.60
    oon
    0.59
    icket
    0.56
    Activations Density 0.209%

    No Known Activations