© 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. 1-RES-JB
    6. 15973
    Prev
    Next
    INDEX
    Explanations

    mentions of international agreements and diplomatic initiatives

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the suffix "ente" in words

    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
    map
    -0.72
    */(
    -0.70
    tub
    -0.70
    Courtesy
    -0.68
    krit
    -0.67
    ODUCT
    -0.67
    pages
    -0.66
    unks
    -0.64
    Spot
    -0.63
    children
    -0.63
    POSITIVE LOGITS
    ente
    1.41
    uous
    0.93
    cest
    0.92
    terness
    0.90
    zon
    0.81
     Marcos
    0.80
     Aires
    0.77
    uve
    0.75
    chnology
    0.75
    ellen
    0.74
    Activations Density 0.008%

    No Known Activations