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. 0-RES-JB
    6. 16116
    Prev
    Next
    INDEX
    Explanations

    phrases related to campaigns or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to specific campaigns or initiatives, particularly those related to societal issues

    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
     Naz
    -0.66
     cruelty
    -0.61
     casualties
    -0.59
     labels
    -0.59
     spo
    -0.59
     refuge
    -0.58
     Integrity
    -0.57
     details
    -0.57
     frames
    -0.57
     spoilers
    -0.57
    POSITIVE LOGITS
    arter
    4.80
    arters
    2.60
    arts
    1.29
    ART
    1.17
    arty
    1.13
    eret
    1.06
    RNA
    1.03
    arth
    0.99
    arted
    0.99
    amber
    0.95
    Activations Density 0.012%

    No Known Activations