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. 9-RES-JB
    6. 15084
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and political leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and comparative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outreach
    -0.36
     dues
    -0.34
     constituents
    -0.32
     recruit
    -0.31
     orb
    -0.30
     moderates
    -0.30
     aggro
    -0.29
    —"
    -0.29
     hazard
    -0.29
     LGBTQ
    -0.29
    POSITIVE LOGITS
     Whilst
    0.44
    =-=-
    0.41
    bley
    0.38
     Conclusion
    0.38
    \/\/
    0.38
    TPPStreamerBot
    0.36
    rawdownloadcloneembedreportprint
    0.36
     SECTION
    0.36
    terday
    0.34
    BBC
    0.34
    Activations Density 2.896%

    No Known Activations