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. 4-RES-JB
    6. 14976
    Prev
    Next
    INDEX
    Explanations

    numeric values and metrics, with a focus on statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to football statistics, specifically rushing and passing yards

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

    No Comments

    Negative Logits
    pps
    -0.77
    ighed
    -0.77
    éĹĺ
    -0.76
    eus
    -0.76
    idon
    -0.75
    ELF
    -0.75
    rex
    -0.75
    coni
    -0.74
    ktop
    -0.72
    eday
    -0.71
    POSITIVE LOGITS
     prowess
    0.89
     duo
    0.84
     inept
    0.83
     ability
    0.78
     talent
    0.76
     rookies
    0.74
     peripher
    0.74
     brilliance
    0.72
     prospects
    0.72
     inacc
    0.72
    Activations Density 0.059%

    No Known Activations