© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 1610
    Prev
    Next
    INDEX
    Explanations

    terms related to online gaming, specifically genres like RPG, MMO, and FPS

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming and online multiplayer formats, particularly RPGs and MMOs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flies
    -0.89
    atom
    -0.83
    ths
    -0.81
    notations
    -0.79
    motion
    -0.78
    meat
    -0.78
    lie
    -0.78
    court
    -0.76
    bee
    -0.76
    film
    -0.75
    POSITIVE LOGITS
    UE
    0.97
    PDATE
    0.96
    Ds
    0.92
    YL
    0.92
    IC
    0.92
    HER
    0.91
    ICAL
    0.90
    BIL
    0.90
    TING
    0.87
    EED
    0.87
    Activations Density 0.069%

    No Known Activations