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. 8-RES-JB
    6. 20738
    Prev
    Next
    INDEX
    Explanations

    terms related to various medical conditions and health issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative health conditions and issues

    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
     Alphabet
    -0.73
     Wem
    -0.72
    eworld
    -0.72
    cale
    -0.71
     Pace
    -0.70
    ertodd
    -0.69
    riel
    -0.68
    DonaldTrump
    -0.68
     DeVos
    -0.67
     Bezos
    -0.66
    POSITIVE LOGITS
     failure
    1.33
     instability
    1.33
     malfunction
    1.28
     exhaustion
    1.24
     collapse
    1.24
     shortages
    1.23
     failures
    1.21
     dysfunction
    1.20
     deterioration
    1.20
     starvation
    1.19
    Activations Density 0.528%

    No Known Activations