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. 2462
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Rod."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns that begin with "rod."

    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
     premiums
    -0.68
     slightest
    -0.65
     nomine
    -0.65
     haz
    -0.63
     totality
    -0.63
    ablishment
    -0.62
     quarters
    -0.61
     unanim
    -0.61
     Pixie
    -0.60
     stakes
    -0.60
    POSITIVE LOGITS
    ynamic
    1.38
    ynam
    1.29
    rod
    1.28
    olph
    1.04
    der
    0.98
    rig
    0.90
    yssey
    0.88
    rome
    0.88
    inson
    0.86
    ollar
    0.85
    Activations Density 0.008%

    No Known Activations