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. 0-RES-JB
    6. 2949
    Prev
    Next
    INDEX
    Explanations

    PvP (Player versus Player) and PvE (Player versus Environment) references in a gaming context

    oai_token-act-pair · gpt-3.5-turbo

    references to the gaming term "Pv" (player versus)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.66
     rad
    -0.65
    lu
    -0.65
    riz
    -0.64
    @#&
    -0.64
     derby
    -0.63
    kos
    -0.63
     magnets
    -0.62
     chants
    -0.62
    ulin
    -0.62
    POSITIVE LOGITS
     Private
    2.96
     Pv
    2.61
     Corpor
    2.32
    Private
    2.28
     corpor
    1.95
     priv
    1.17
    private
    1.14
     Operator
    1.11
     Priv
    1.10
     Petty
    1.04
    Activations Density 0.027%

    No Known Activations