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. 3-RES-JB
    6. 14271
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Sou" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "Sou" and its variations, indicating a focus on a specific person or topic associated with that name

    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
     Bermuda
    -0.79
    OY
    -0.76
    è¦ļéĨĴ
    -0.74
     CPC
    -0.72
     Clarkson
    -0.70
     Pax
    -0.66
    GMT
    -0.65
    Ö¼
    -0.65
    aceous
    -0.63
    utic
    -0.62
    POSITIVE LOGITS
    ven
    1.06
    quet
    0.97
    reth
    0.96
    velt
    0.94
    cery
    0.92
    plet
    0.90
    pling
    0.88
    rend
    0.88
    hou
    0.87
     Sou
    0.86
    Activations Density 0.007%

    No Known Activations