© 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. 4-RES-JB
    6. 20228
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    elements related to names and references to individuals, particularly in a narrative context

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

    No Comments

    Negative Logits
    lished
    -0.75
    âĢ¢âĢ¢
    -0.73
    é¾
    -0.68
    ãĤ±
    -0.65
     kcal
    -0.62
    ãĤ¦
    -0.61
    éŃĶ
    -0.61
    uese
    -0.60
    SpaceEngineers
    -0.60
    ãĥĩ
    -0.60
    POSITIVE LOGITS
    iasis
    0.77
    mort
    0.73
    ttle
    0.70
    mology
    0.68
    alus
    0.67
    agos
    0.66
    pipe
    0.66
    aya
    0.65
    azine
    0.65
    inge
    0.65
    Activations Density 0.087%

    No Known Activations