© 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. 9045
    Prev
    Next
    INDEX
    Explanations

    words related to emotions and desires, particularly those related to pent-up emotions such as anger, frustration, and desire

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to emotional release and venting frustrations

    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
    document
    -0.81
     Zup
    -0.77
    iture
    -0.69
    guide
    -0.67
    arthed
    -0.67
    escription
    -0.65
    facing
    -0.65
    oval
    -0.65
    joining
    -0.65
    ording
    -0.65
    POSITIVE LOGITS
     passions
    1.52
     thirst
    1.45
     appetite
    1.41
     emotions
    1.36
     craving
    1.35
     urges
    1.31
     imagination
    1.27
     instincts
    1.27
     curiosity
    1.26
     fears
    1.26
    Activations Density 0.579%

    No Known Activations