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. 23759
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term "FaZe" along with related terms and actions associated with the entity

    oai_token-act-pair · gpt-3.5-turbo

    references to game titles and esports 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
     recess
    -0.74
     latitude
    -0.69
    ivities
    -0.69
     property
    -0.67
    cknowled
    -0.66
    \/\/
    -0.65
     principals
    -0.65
     Betsy
    -0.65
     MFT
    -0.65
    thia
    -0.65
    POSITIVE LOGITS
     Esports
    1.14
     eSports
    1.13
     Wolves
    1.01
     Gaming
    0.89
     Zerg
    0.89
     Protoss
    0.88
     Starcraft
    0.85
     Fnatic
    0.85
     Dota
    0.83
     esports
    0.81
    Activations Density 0.153%

    No Known Activations