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. 1-RES-JB
    6. 17771
    Prev
    Next
    INDEX
    Explanations

    mentions of the term 'Masters', potentially related to academia, skills, titles, or competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to "Masters," indicating a focus on mastery or significant achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.73
    tical
    -0.68
    irrel
    -0.67
    rine
    -0.67
    gged
    -0.65
    kefeller
    -0.64
    ople
    -0.62
    ITE
    -0.60
    tics
    -0.60
    OPLE
    -0.60
    POSITIVE LOGITS
     Masters
    1.09
    masters
    0.94
    essor
    0.89
    ĨĴ
    0.82
    antis
    0.77
    Wallet
    0.74
    iless
    0.74
     masters
    0.73
     Swordsman
    0.73
    quartered
    0.72
    Activations Density 0.008%

    No Known Activations