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. 9726
    Prev
    Next
    INDEX
    Explanations

    references to bags

    oai_token-act-pair · gpt-3.5-turbo

    references to bags

    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
     Edmund
    -0.75
     Galile
    -0.68
     Emin
    -0.68
     spect
    -0.67
    issance
    -0.67
    terday
    -0.66
     Democr
    -0.64
     relations
    -0.63
    vironment
    -0.62
     Kepler
    -0.60
    POSITIVE LOGITS
    ging
    1.32
    gie
    1.28
    gery
    1.27
    ged
    1.26
    glers
    1.17
    bag
    1.16
    bags
    1.09
    loads
    1.07
    gers
    1.04
    pipe
    1.00
    Activations Density 0.034%

    No Known Activations