© 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. 16716
    Prev
    Next
    INDEX
    Explanations

    people expressing strong emotional responses or opinions about something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong affection or appreciation

    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
    pload
    -0.71
     plur
    -0.62
     Journals
    -0.61
    ATURES
    -0.59
     countdown
    -0.58
     unanim
    -0.57
    ORTS
    -0.57
    Quantity
    -0.56
    prints
    -0.56
     mole
    -0.56
    POSITIVE LOGITS
    entimes
    0.83
     nowadays
    0.81
     during
    0.78
    ingu
    0.77
    .
    0.74
     ðŁĺ
    0.73
     when
    0.70
     because
    0.69
    aws
    0.69
     anymore
    0.69
    Activations Density 0.117%

    No Known Activations