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. 10-RES-JB
    6. 22417
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various fields and topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports events and competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "!
    -0.70
    $.
    -0.65
    depending
    -0.64
    ":{"
    -0.64
    WASHINGTON
    -0.63
    USA
    -0.63
     Written
    -0.62
    ASHINGTON
    -0.62
    ÃĽ
    -0.62
     Canaver
    -0.61
    POSITIVE LOGITS
     debacle
    0.80
     fiasco
    0.78
     notwithstanding
    0.71
     stuffing
    0.63
     playbook
    0.62
     bumper
    0.62
     ($
    0.61
     staples
    0.61
     standout
    0.60
     motif
    0.60
    Activations Density 0.650%

    No Known Activations