© 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. 8-RES-JB
    11. 18641
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing a positive outlook or situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions affirming the concept of something being a "good thing."

    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
     largeDownload
    -0.72
    hod
    -0.72
    geons
    -0.68
    claimed
    -0.66
    asers
    -0.63
     sockets
    -0.63
     furnish
    -0.62
    cled
    -0.62
     haze
    -0.61
    oufl
    -0.59
    POSITIVE LOGITS
     happened
    1.00
     happening
    0.95
    iverse
    0.91
     happen
    0.90
     happens
    0.86
     happ
    0.78
     Happ
    0.78
     imaginable
    0.75
    ially
    0.75
    iola
    0.71
    Activations Density 0.042%

    No Known Activations