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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 13184
    Prev
    Next
    INDEX
    Explanations

    specific acronyms related to MMORPGs (Massively Multiplayer Online Role-Playing Games)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "MM" related to a specific game or franchise context

    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
    swick
    -0.81
     McCartney
    -0.75
    hold
    -0.75
     Coul
    -0.74
    patrick
    -0.73
    ãĥ´ãĤ¡
    -0.73
    atchewan
    -0.71
    ulkan
    -0.71
    choes
    -0.69
     Solitaire
    -0.68
    POSITIVE LOGITS
    ORPG
    1.84
    MM
    0.99
    FG
    0.95
    QB
    0.91
    ONEY
    0.90
    ategory
    0.81
    achine
    0.80
    ITH
    0.77
    RL
    0.77
    IAS
    0.74
    Activations Density 0.007%

    No Known Activations