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. 4-RES-JB
    6. 23247
    Prev
    Next
    INDEX
    Explanations

    keywords related to player versus player (PvP) elements in a game

    oai_token-act-pair · gpt-3.5-turbo

    terms related to player versus environment (PvE) and player versus player (PvP) gaming contexts

    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
     GOODMAN
    -0.95
    ãĥ³ãĤ¸
    -0.94
    umbn
    -0.77
    ptin
    -0.74
    Catal
    -0.71
    è¦ļéĨĴ
    -0.70
    natureconservancy
    -0.70
    abetic
    -0.70
    INA
    -0.69
    é¾įåĸļ士
    -0.69
    POSITIVE LOGITS
     Pv
    0.89
    folios
    0.80
    ties
    0.79
    lyak
    0.76
    queue
    0.75
    ivot
    0.73
    kie
    0.73
    riors
    0.72
    ilon
    0.71
    tp
    0.71
    Activations Density 0.016%

    No Known Activations