Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8842
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, places, or concepts involving the term "Grand"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Grand" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tcp
    -0.74
    ivity
    -0.72
    iod
    -0.67
    jab
    -0.67
    isms
    -0.66
     borne
    -0.66
     iodine
    -0.65
     perpend
    -0.64
    onomy
    -0.64
    д
    -0.64
    POSITIVE LOGITS
     Grand
    3.67
    Grand
    3.03
     grand
    2.18
    grand
    2.10
     Grande
    1.36
     Gran
    1.31
     grandma
    1.23
     Masonic
    1.11
     Freem
    1.11
     grandchildren
    1.10
    Activations Density 0.012%

    No Known Activations