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. 2513
    Prev
    Next
    INDEX
    Explanations

    terms related to Massive Multiplayer Online Role-Playing Games (MMORPGs)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "MMORPG" and its variations

    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
    ãĥ´ãĤ¡
    -0.84
    swick
    -0.80
     McCartney
    -0.74
     Barcl
    -0.68
    hold
    -0.68
    ĸļ
    -0.68
    amus
    -0.67
    choes
    -0.67
     Sakuya
    -0.66
    atchewan
    -0.66
    POSITIVE LOGITS
    ORPG
    1.80
    MM
    1.11
    achine
    0.93
    QB
    0.87
    FG
    0.80
    ITH
    0.80
    ONEY
    0.78
    ategory
    0.78
    SE
    0.78
    ajor
    0.77
    Activations Density 0.006%

    No Known Activations