Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9082
    Prev
    Next
    INDEX
    Explanations

    words related to strong feelings or extreme interests, particularly the word "obsessed."

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating strong emotional states or conditions, particularly obsession and addiction

    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
     contention
    -0.74
     visibility
    -0.68
    shine
    -0.67
     inclusion
    -0.66
    work
    -0.64
     clearance
    -0.64
     Exit
    -0.63
     Formation
    -0.62
     clarity
    -0.61
     form
    -0.61
    POSITIVE LOGITS
     addicted
    2.56
     obsessed
    2.43
     allergic
    1.40
     jealous
    1.37
     fascinated
    1.37
     accustomed
    1.36
     possessed
    1.35
     offended
    1.33
     incapable
    1.32
     afflicted
    1.32
    Activations Density 0.029%

    No Known Activations