© 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. 0-RES-JB
    11. 13976
    Prev
    Next
    INDEX
    Explanations

    adverbs expressing an emotion or state of being followed by words representing a positive or negative characteristic

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that convey emotional intensity or attitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icable
    -0.70
    ausible
    -0.67
    mental
    -0.67
    ication
    -0.66
     adequate
    -0.66
     affect
    -0.66
     perception
    -0.65
     consolidation
    -0.65
     separ
    -0.65
     physical
    -0.65
    POSITIVE LOGITS
     proudly
    2.44
     calmly
    2.43
     confidently
    2.37
     angrily
    2.31
     patiently
    2.30
     politely
    2.29
     enthusiastically
    2.27
     loudly
    2.19
     boldly
    2.17
     nervously
    2.10
    Activations Density 0.069%

    No Known Activations