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. 4957
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ro" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Ro" followed by numbers or relevant nouns, indicating a focus on a specific subject or concept related to "Ro."

    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
    ividual
    -0.77
    mercial
    -0.72
     CPC
    -0.70
     Consent
    -0.69
    manship
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.69
    lihood
    -0.68
     EntityItem
    -0.65
     Yankee
    -0.64
     Schumer
    -0.64
    POSITIVE LOGITS
    java
    1.09
    oster
    1.06
    vers
    1.02
    asted
    0.99
    aches
    0.98
    zzi
    0.96
    zeb
    0.95
    aming
    0.94
    oke
    0.92
    zz
    0.91
    Activations Density 0.017%

    No Known Activations