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. 11655
    Prev
    Next
    INDEX
    Explanations

    positions and roles in sports

    oai_token-act-pair · gpt-3.5-turbo

    sports positions and player roles

    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
     redes
    -0.69
    urat
    -0.67
    INFO
    -0.67
    ilogy
    -0.66
     therap
    -0.66
    Climate
    -0.65
    atown
    -0.64
    abus
    -0.63
    States
    -0.62
     airlines
    -0.62
    POSITIVE LOGITS
     Brandon
    1.27
     Aaron
    1.24
     Jason
    1.22
     Kyle
    1.22
     Reggie
    1.21
     Kevin
    1.21
     Justin
    1.21
     Joey
    1.19
     Jared
    1.19
     Danny
    1.19
    Activations Density 0.090%

    No Known Activations