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. 2-RES-JB
    6. 8832
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific type of online gaming, possibly involving player versus player (PvP) combat mechanics and characters like Pogba

    oai_token-act-pair · gpt-3.5-turbo

    mentions of player versus player (PvP) content and related terminology in gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.80
     Leilan
    -0.73
    è¦ļéĨĴ
    -0.72
    */(
    -0.71
     Cth
    -0.71
     Faw
    -0.67
    chell
    -0.67
     excuses
    -0.66
    umbn
    -0.65
     Chrys
    -0.65
    POSITIVE LOGITS
     Pv
    1.11
    riors
    0.81
    inion
    0.80
    endix
    0.79
    rint
    0.77
    ledged
    0.76
    vp
    0.76
    itting
    0.75
    tp
    0.73
    ivot
    0.73
    Activations Density 0.019%

    No Known Activations