© 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. 1-RES-JB
    11. 15671
    Prev
    Next
    INDEX
    Explanations

    references to words related to large, powerful, and dominating entities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "juggle" or related terms

    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
     sentencing
    -0.69
    oral
    -0.67
    */(
    -0.64
     diam
    -0.63
    bleacher
    -0.62
    idem
    -0.61
    adder
    -0.61
     Loyal
    -0.61
     Edmund
    -0.61
    treatment
    -0.60
    POSITIVE LOGITS
    ernaut
    1.47
     jugg
    1.43
     juggling
    1.27
    glers
    1.03
    adelphia
    0.98
    ãĥ¼ãĤ¯
    0.95
    alos
    0.88
    TAIN
    0.84
    erella
    0.82
    alo
    0.79
    Activations Density 0.006%

    No Known Activations