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

    Neuronpedia

    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. 11363
    Prev
    Next
    INDEX
    Explanations

    adjectives related to negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness

    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
    •layer 10 - sadness

    No Comments

    Negative Logits
    aeda
    -0.74
    rity
    -0.69
    ouver
    -0.67
     fielded
    -0.65
    ensibly
    -0.65
    Testing
    -0.65
     streng
    -0.64
    uve
    -0.64
     vetted
    -0.64
     hyd
    -0.63
    POSITIVE LOGITS
    omas
    1.26
    istic
    1.20
    der
    1.16
    istically
    1.13
    omic
    1.00
    stal
    0.85
    faced
    0.81
     fate
    0.81
    ful
    0.80
    ous
    0.79
    Activations Density 0.069%

    No Known Activations