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. 2-RES-JB
    6. 10110
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically focusing on the name "Jac"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jac," indicating a focus on individuals or characters with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -0.76
    é¾
    -0.76
    culosis
    -0.75
    gage
    -0.72
    awar
    -0.71
     Dull
    -0.71
     APPLIC
    -0.67
    powder
    -0.64
    spring
    -0.64
     ND
    -0.63
    POSITIVE LOGITS
     Jac
    1.06
    lyn
    1.05
    Jac
    1.05
    obal
    0.86
     Brun
    0.77
     Jacqu
    0.76
    obe
    0.75
    emet
    0.73
    illian
    0.73
    leen
    0.70
    Activations Density 0.014%

    No Known Activations