© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11193
    Prev
    Next
    INDEX
    Explanations

    legal concepts related to ownership and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating requirements or suggestions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.67
     Survivors
    -0.64
     phantom
    -0.59
    ellow
    -0.58
    ãĥ³
    -0.58
    é¾įåĸļ士
    -0.57
     recount
    -0.57
     unin
    -0.57
    soType
    -0.56
    yth
    -0.55
    POSITIVE LOGITS
     choice
    0.73
     choices
    0.73
     hire
    0.71
     invariably
    0.71
     easiest
    0.70
    starter
    0.70
     resorted
    0.69
    choice
    0.69
     gladly
    0.69
     preferably
    0.69
    Activations Density 0.185%

    No Known Activations