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. 3-RES-JB
    6. 1624
    Prev
    Next
    INDEX
    Explanations

    words related to the video game "Counter-Strike"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to video games, particularly around the "Counter-Strike" and "Call of Duty" franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    option
    -0.69
     Kavanaugh
    -0.65
    comings
    -0.64
    inges
    -0.63
    hillary
    -0.63
     liner
    -0.63
     UW
    -0.61
     Shel
    -0.61
    requires
    -0.59
    rez
    -0.59
    POSITIVE LOGITS
    engeance
    0.78
     ®
    0.77
     imitation
    0.76
    axies
    0.74
     Crate
    0.70
    ciating
    0.68
    tics
    0.67
    qus
    0.67
    vation
    0.67
    atoes
    0.67
    Activations Density 0.121%

    No Known Activations