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. 11-RES-JB
    6. 10486
    Prev
    Next
    INDEX
    Explanations

    short phrases indicating the delivery of news or stories in the mornings

    oai_token-act-pair · gpt-3.5-turbo

    references to news or information being delivered, particularly in a digital format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.51
    lihood
    -0.49
     dialect
    -0.49
    arkin
    -0.49
     Enix
    -0.48
     band
    -0.48
    illon
    -0.48
     Zot
    -0.48
    abase
    -0.48
     sequ
    -0.47
    POSITIVE LOGITS
    $$$$
    0.63
    usat
    0.60
     Please
    0.55
    Subscribe
    0.55
    Email
    0.54
    ugs
    0.54
     Dozens
    0.54
     Try
    0.54
    Cu
    0.53
     sidx
    0.53
    Activations Density 0.027%

    No Known Activations