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. 6-RES-JB
    6. 10403
    Prev
    Next
    INDEX
    Explanations

    keywords related to living conditions or environments

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "living" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.91
    reg
    -0.90
    osen
    -0.82
    pport
    -0.79
    IFIC
    -0.77
    achu
    -0.77
    eca
    -0.75
    uyomi
    -0.74
    asus
    -0.73
    elight
    -0.70
    POSITIVE LOGITS
     Wage
    1.06
    lihood
    1.04
     wage
    0.86
    hart
    0.85
     quarters
    0.80
     wills
    0.79
     liv
    0.79
    living
    0.74
    ths
    0.74
     rooms
    0.73
    Activations Density 0.032%

    No Known Activations