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. 20680
    Prev
    Next
    INDEX
    Explanations

    important names and titles mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their titles or roles in organizations

    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
    groups
    -0.69
    articles
    -0.69
     plantations
    -0.67
     armies
    -0.67
     pockets
    -0.67
     cartels
    -0.67
    âĸ¬
    -0.66
     nests
    -0.65
    pees
    -0.64
     loopholes
    -0.63
    POSITIVE LOGITS
     coordinator
    1.26
     director
    1.25
     chairman
    1.23
     commissioner
    1.15
     Coordinator
    1.15
    director
    1.14
     ambassador
    1.12
     deputy
    1.12
     liaison
    1.10
     manager
    1.10
    Activations Density 0.274%

    No Known Activations