© 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. 7795
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving awards or honors

    oai_token-act-pair · gpt-3.5-turbo

    references to military medals and awards for valor

    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
    odcast
    -0.79
    yout
    -0.79
    oby
    -0.74
     predators
    -0.72
    wolves
    -0.72
    loop
    -0.71
    anwhile
    -0.71
     noisy
    -0.71
    glers
    -0.71
    ombies
    -0.70
    POSITIVE LOGITS
     honorary
    1.54
     Medal
    1.42
     medals
    1.39
     medal
    1.35
     honors
    1.35
     honour
    1.31
     accol
    1.27
     Medals
    1.24
    inguished
    1.23
     honor
    1.22
    Activations Density 0.279%

    No Known Activations