© 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. 9-RES-JB
    11. 18382
    Prev
    Next
    INDEX
    Explanations

    words related to emotional states, particularly negative emotions like awkwardness, awfulness, and awakeness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions, particularly those conveying surprise or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Townsend
    -0.72
    cision
    -0.71
     iod
    -0.64
     Feld
    -0.64
     Luxem
    -0.62
     Missile
    -0.60
     Nadu
    -0.60
    idated
    -0.59
    ogue
    -0.59
     leaflets
    -0.58
    POSITIVE LOGITS
    kward
    1.46
    akening
    1.39
    akens
    1.36
    esome
    1.19
    dry
    1.05
    aii
    1.04
    orld
    1.00
    aken
    1.00
    apon
    0.98
    riter
    0.95
    Activations Density 0.024%

    No Known Activations