© 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. 3-RES-JB
    11. 14725
    Prev
    Next
    INDEX
    Explanations

    references to the word "Mash" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to "mash" and related terms in various contexts

    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
    vernment
    -0.92
    ĪĴ
    -0.90
    elaide
    -0.85
     Defenders
    -0.81
    wcs
    -0.81
    ©¶æ
    -0.72
    ¥µ
    -0.68
    etheless
    -0.67
    DragonMagazine
    -0.66
    notation
    -0.65
    POSITIVE LOGITS
     Mash
    1.11
     mash
    0.95
     tun
    0.89
    \/\/
    0.86
    Mix
    0.84
    adow
    0.82
    pee
    0.80
     potatoes
    0.79
    burn
    0.78
    apan
    0.77
    Activations Density 0.004%

    No Known Activations