© 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. 18664
    Prev
    Next
    INDEX
    Explanations

    phrases related to the word "semi"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of semiautomatic weapons or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Nanto
    -0.69
     Brooks
    -0.67
    icators
    -0.63
     Franks
    -0.60
     Bark
    -0.59
     fingertips
    -0.58
    nia
    -0.58
     DRAG
    -0.57
     guts
    -0.56
     Tigers
    -0.56
    POSITIVE LOGITS
    -)
    1.12
    -
    1.08
    -[
    1.01
    -'
    0.96
     versa
    0.95
    -.
    0.94
    urban
    0.93
    atomic
    0.92
    atural
    0.91
    lethal
    0.89
    Activations Density 0.023%

    No Known Activations