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. 7-RES-JB
    6. 4767
    Prev
    Next
    INDEX
    Explanations

    content related to multiplayer modes in video games

    oai_token-act-pair · gpt-3.5-turbo

    components related to video games and gaming culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Explan
    -0.65
     worsened
    -0.57
     affidavit
    -0.56
    anwhile
    -0.55
     Hasan
    -0.55
     coerc
    -0.54
     omission
    -0.54
     cler
    -0.53
     Biden
    -0.52
     spokesman
    -0.52
    POSITIVE LOGITS
     guiActiveUnfocused
    0.72
     genre
    0.69
     franchises
    0.68
     eSports
    0.68
     esports
    0.67
     fanbase
    0.66
     tournaments
    0.65
     illustrious
    0.64
    ports
    0.62
    Arcade
    0.62
    Activations Density 1.200%

    No Known Activations