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. 11-RES-JB
    6. 7901
    Prev
    Next
    INDEX
    Explanations

    adjectives describing negative emotions or difficulties

    oai_token-act-pair · gpt-3.5-turbo

    words that convey difficulty or negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constructs
    -0.88
    events
    -0.88
     channels
    -0.84
    markets
    -0.84
     levers
    -0.82
    units
    -0.82
    items
    -0.80
    frames
    -0.80
     centres
    -0.80
    classes
    -0.80
    POSITIVE LOGITS
     complexion
    0.97
     awakening
    0.90
     relapse
    0.87
     streak
    0.85
     chuckle
    0.83
     welcome
    0.83
     glance
    0.82
     laugh
    0.81
     halt
    0.81
     fate
    0.81
    Activations Density 0.153%

    No Known Activations