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. 16481
    Prev
    Next
    INDEX
    Explanations

    phrases related to large quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     abduct
    -0.81
    natureconservancy
    -0.77
     neck
    -0.74
     affili
    -0.74
     necks
    -0.74
     scenery
    -0.73
     guise
    -0.73
     brief
    -0.72
     imperson
    -0.72
     heav
    -0.72
    POSITIVE LOGITS
     Assuming
    1.32
     Compare
    1.27
     That
    1.20
     Including
    1.15
     Meanwhile
    1.14
     Considering
    1.12
     Compared
    1.10
     Its
    1.04
     Additionally
    1.04
     Wow
    1.03
    Activations Density 0.429%

    No Known Activations