© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3284
    Prev
    Next
    INDEX
    Explanations

    phrases related to close relationships or strong emotional connections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "best."

    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
    cano
    -0.76
    zanne
    -0.64
     abolished
    -0.63
     outlawed
    -0.63
     OUR
    -0.61
    leted
    -0.60
    umat
    -0.57
    ller
    -0.56
    letal
    -0.55
    zzi
    -0.55
    POSITIVE LOGITS
    seller
    1.14
     friend
    1.03
    iary
    1.02
    friend
    0.98
     intentions
    0.96
    iaries
    0.94
     Friend
    0.91
     efforts
    0.90
     wishes
    0.88
     instincts
    0.87
    Activations Density 0.048%

    No Known Activations