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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 8024
    Prev
    Next
    INDEX
    Explanations

    phrases or words that describe or refer to opposing teams or players

    oai_token-act-pair · gpt-3.5-turbo

    terms related to opposition in competitive contexts, particularly in sports

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

    No Comments

    Negative Logits
    doc
    -0.93
    milo
    -0.92
    opian
    -0.86
    wik
    -0.82
    Progress
    -0.80
    enegger
    -0.80
    clus
    -0.80
    ding
    -0.78
    docs
    -0.78
    Compan
    -0.77
    POSITIVE LOGITS
     batters
    0.93
     defenses
    0.90
     strugg
    0.86
     defences
    0.84
     attacker
    0.78
     passer
    0.77
     stare
    0.76
     scout
    0.76
     scouting
    0.76
     intruder
    0.76
    Activations Density 0.025%

    No Known Activations