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. 8639
    Prev
    Next
    INDEX
    Explanations

    references to statistics such as yards gained, carries, tackles, and points scored in various sports

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas

    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
    ²¾
    -0.81
    itarian
    -0.78
    )=(
    -0.77
    ¬¼
    -0.73
    ribe
    -0.71
    FactoryReloaded
    -0.71
    eral
    -0.70
    izoph
    -0.69
    opsy
    -0.69
    dden
    -0.69
    POSITIVE LOGITS
     averaging
    1.22
     including
    1.06
     tying
    1.04
     totaling
    1.03
     surpass
    1.03
     completing
    1.00
     topping
    0.98
     finishing
    0.96
     ranking
    0.96
     scoring
    0.95
    Activations Density 0.066%

    No Known Activations