Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 14665
    Prev
    Next
    INDEX
    Explanations

    words related to sports, particularly focused on Australian football league (NRL) and players

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to sports, particularly focusing on league and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.75
    ages
    -0.66
    roma
    -0.66
    Paris
    -0.66
     Venice
    -0.65
    ICAN
    -0.65
    igation
    -0.64
    Nob
    -0.63
    aired
    -0.63
    icans
    -0.63
    POSITIVE LOGITS
     NSW
    1.21
    elong
    1.07
     NRL
    1.07
     Queensland
    1.03
     Australians
    1.03
     Tasmania
    1.00
     NZ
    0.98
     Turnbull
    0.96
    iership
    0.96
     Adelaide
    0.94
    Activations Density 0.058%

    No Known Activations