© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5307
    Prev
    Next
    INDEX
    Explanations

    words related to mental and emotional states, such as frustrations, creativity, soul, influence, power, thoughts, energy, magic, gratitude, and spell

    oai_token-act-pair · gpt-3.5-turbo

    themes related to power, influence, and emotional expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    whose
    -0.70
    interstitial
    -0.58
    aughed
    -0.57
     Institution
    -0.56
    ossal
    -0.55
    that
    -0.55
     unforeseen
    -0.54
    rising
    -0.54
     Aircraft
    -0.54
     childbirth
    -0.53
    POSITIVE LOGITS
     wisely
    1.08
     responsibly
    0.89
     selves
    0.88
     peacefully
    0.85
     faithfully
    0.85
     carefully
    0.84
     freely
    0.84
     diligently
    0.83
    mates
    0.78
     elsewhere
    0.77
    Activations Density 0.270%

    No Known Activations