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. 1629
    Prev
    Next
    INDEX
    Explanations

    keywords related to news and politics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Related" indicating connections to other articles or topics

    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
    arer
    -0.86
    arest
    -0.78
    ample
    -0.70
    eg
    -0.69
    ãĤ©
    -0.69
    veland
    -0.67
    agall
    -0.66
    acers
    -0.66
    UGE
    -0.66
    ils
    -0.64
    POSITIVE LOGITS
     Cosponsors
    0.92
     Stories
    0.89
    Related
    0.87
     Factors
    0.79
     Develop
    0.77
     Related
    0.77
     Laugh
    0.74
    imedia
    0.74
     Topics
    0.74
     Occupations
    0.73
    Activations Density 0.011%

    No Known Activations