© 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. 6-RES-JB
    11. 10709
    Prev
    Next
    INDEX
    Explanations

    phrases related to an increase or uptick in various events or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating trends or increases in various statistics or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mates
    -0.72
    acle
    -0.70
    atta
    -0.69
     nearest
    -0.69
     stump
    -0.67
     describ
    -0.65
     disapp
    -0.62
    most
    -0.62
     ceases
    -0.62
    abl
    -0.61
    POSITIVE LOGITS
    catentry
    0.74
    risome
    0.66
     circulating
    0.66
    ergic
    0.64
    ItemImage
    0.64
     popularity
    0.63
     misinformation
    0.61
     consultations
    0.61
     prosecutions
    0.61
     casualties
    0.61
    Activations Density 0.193%

    No Known Activations