Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 646
    Prev
    Next
    INDEX
    Explanations

    references to the word "Mass"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mass" in various contexts, likely related to a specific subject or phenomenon such as the "Mass Effect" series or other occurrences involving the term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bil
    -0.77
     ponies
    -0.74
    gered
    -0.69
     pony
    -0.69
    gers
    -0.67
    warts
    -0.64
    BILITIES
    -0.64
    stal
    -0.64
     Korra
    -0.63
     Slovenia
    -0.62
    POSITIVE LOGITS
    achus
    1.49
    achusetts
    1.40
    acre
    1.10
    achu
    1.03
    imil
    1.03
    imo
    1.02
    arella
    1.01
    enary
    0.98
    illon
    0.96
    assi
    0.95
    Activations Density 0.017%

    No Known Activations