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. 16432
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports team performance and qualifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive qualifications and game stages in sports

    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
    hart
    -0.83
    kinson
    -0.79
    imaru
    -0.75
    argon
    -0.75
    ogun
    -0.72
    sonian
    -0.71
    arre
    -0.69
    baugh
    -0.67
     Spears
    -0.66
    footed
    -0.65
    POSITIVE LOGITS
     finals
    1.22
     semifinals
    1.16
    finals
    1.05
     qualifier
    1.03
     standings
    1.03
     finalists
    1.03
     elimination
    0.98
     winners
    0.97
     qualifiers
    0.97
     Winners
    0.96
    Activations Density 0.147%

    No Known Activations