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. 24144
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "Tri" or "three"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Tri" and its variations, indicating a focus on triangular or three-part concepts

    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
    manship
    -0.77
     deed
    -0.74
     IST
    -0.69
     deeds
    -0.67
    INESS
    -0.65
     CPC
    -0.65
     deduction
    -0.65
     saline
    -0.64
     Goods
    -0.62
    nikov
    -0.61
    POSITIVE LOGITS
    pling
    1.14
    assic
    1.05
    ppy
    1.03
    adic
    1.01
    ples
    1.01
    pled
    0.97
    umph
    0.94
    plets
    0.94
    ply
    0.94
    pped
    0.94
    Activations Density 0.016%

    No Known Activations