© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12454
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names ending in 'ius'

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ius" associated with names or terms

    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
     weeks
    -0.69
     caution
    -0.67
     Standard
    -0.66
    GAN
    -0.60
     CAM
    -0.58
     canv
    -0.58
     mood
    -0.58
     plastics
    -0.58
     CBC
    -0.57
     decent
    -0.56
    POSITIVE LOGITS
    ius
    4.54
    ios
    1.54
    inus
    1.50
    cius
    1.41
    imus
    1.40
    ious
    1.40
    io
    1.36
    itus
    1.36
    ior
    1.29
    iatus
    1.28
    Activations Density 0.008%

    No Known Activations