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. 19959
    Prev
    Next
    INDEX
    Explanations

    descriptions or references related to dogs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dog."

    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
    éĹĺ
    -0.81
    oulos
    -0.76
    esson
    -0.73
    ORN
    -0.72
    kefeller
    -0.72
     Edison
    -0.71
    artz
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.69
    farious
    -0.69
    itures
    -0.68
    POSITIVE LOGITS
     dog
    0.98
     dogs
    0.97
    patch
    0.96
     barking
    0.95
    meat
    0.92
    Dog
    0.91
    fighter
    0.90
     pup
    0.88
     puppy
    0.87
     puppies
    0.87
    Activations Density 0.021%

    No Known Activations