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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16445
    Prev
    Next
    INDEX
    Explanations

    names of soccer players

    oai_token-act-pair · gpt-3.5-turbo

    names and mentions of professional soccer players and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Navajo
    -0.90
     Cherokee
    -0.89
     legislatures
    -0.84
    aucus
    -0.84
    Larry
    -0.84
    Anonymous
    -0.83
    GOP
    -0.82
     Cindy
    -0.82
    achusetts
    -0.82
     Interstate
    -0.82
    POSITIVE LOGITS
     Juventus
    1.10
     sacked
    1.07
     striker
    1.06
     goalkeeper
    1.06
     winger
    1.05
     midfielder
    1.04
     footballer
    1.01
     Sunderland
    1.01
     Liverpool
    1.01
     £
    1.01
    Activations Density 0.280%

    No Known Activations