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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 5344
    Prev
    Next
    INDEX
    Explanations

    terms related to negative states or conditions, such as poor health, slowing economic growth, and bodily discomfort

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health issues and economic decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    augh
    -0.72
    ittees
    -0.71
    Ru
    -0.69
    adult
    -0.68
    Cru
    -0.68
    ften
    -0.68
    Lie
    -0.67
    adv
    -0.64
    roo
    -0.64
     proudly
    -0.63
    POSITIVE LOGITS
     morale
    0.99
     mobility
    0.95
     performance
    0.89
     connectivity
    0.89
     supply
    0.85
     finances
    0.84
     enrollment
    0.84
     circulation
    0.82
     visitation
    0.81
     balance
    0.81
    Activations Density 0.326%

    No Known Activations