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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17423
    Prev
    Next
    INDEX
    Explanations

    descriptions related to emotional states and experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional states or sentiments in various contexts

    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
    entials
    -0.68
    sheet
    -0.67
    spec
    -0.66
    multiple
    -0.65
    levant
    -0.65
    Export
    -0.64
     pipeline
    -0.64
     MAP
    -0.63
    MAP
    -0.63
     Modified
    -0.62
    POSITIVE LOGITS
     melancholy
    1.07
     pity
    1.04
     bitters
    0.98
     sadness
    0.95
     cynicism
    0.93
     sorrow
    0.91
     melanch
    0.89
     understatement
    0.88
     amused
    0.87
     scarcely
    0.86
    Activations Density 0.889%

    No Known Activations