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. 3-RES-JB
    6. 7515
    Prev
    Next
    INDEX
    Explanations

    names of sports analysts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals related to sports commentary and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traged
    -0.87
     cryst
    -0.77
     destro
    -0.76
     warr
    -0.76
     uneasy
    -0.73
     conflic
    -0.72
     paths
    -0.72
     separation
    -0.71
     trave
    -0.71
     dependencies
    -0.71
    POSITIVE LOGITS
     Kobe
    0.99
    hots
    0.85
    bucks
    0.83
    obyl
    0.77
    agne
    0.75
    ingo
    0.75
     Limbaugh
    0.73
    culosis
    0.73
    ����
    0.73
    atu
    0.72
    Activations Density 0.034%

    No Known Activations