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. 7-RES-JB
    6. 9061
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and activism

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding the contributions and impacts of international organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raft
    -0.78
     Deadline
    -0.71
     Emails
    -0.71
    ursday
    -0.69
    DragonMagazine
    -0.67
    owler
    -0.64
     Ports
    -0.64
    ATS
    -0.64
     Pump
    -0.62
    peed
    -0.61
    POSITIVE LOGITS
     morally
    1.05
     socially
    1.01
     subord
    1.01
     oneself
    0.98
    ).[
    0.95
     societal
    0.94
     emanc
    0.94
     therein
    0.92
     intellectually
    0.92
     society
    0.91
    Activations Density 1.479%

    No Known Activations