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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13738
    Prev
    Next
    INDEX
    Explanations

    names related to proper nouns that end with "on"

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to individuals and organizations

    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
    resents
    -0.77
    sylvania
    -0.72
     ECO
    -0.67
    «ĺ
    -0.67
    cellent
    -0.66
    ļéĨĴ
    -0.66
    Ĺ
    -0.65
    etitive
    -0.62
    DragonMagazine
    -0.61
    odcast
    -0.61
    POSITIVE LOGITS
    izon
    0.83
    aji
    0.82
    isen
    0.82
     Aur
    0.82
    vana
    0.79
    ril
    0.76
    ali
    0.74
    als
    0.74
    ayn
    0.74
     ali
    0.73
    Activations Density 0.012%

    No Known Activations