© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20425
    Prev
    Next
    INDEX
    Explanations

    references to large groups of individuals or populations

    oai_token-act-pair · gpt-3.5-turbo

    quantities and statistics related to people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.75
     manag
    -0.75
    inventoryQuantity
    -0.74
     superiors
    -0.68
     nicely
    -0.66
     Conclusion
    -0.65
    major
    -0.63
     competence
    -0.62
     midway
    -0.62
     srfAttach
    -0.61
    POSITIVE LOGITS
     perished
    1.22
     died
    1.03
     illegally
    1.03
     marched
    1.00
     die
    0.94
     perish
    0.91
     crammed
    0.86
     poured
    0.86
     streamed
    0.85
     annually
    0.85
    Activations Density 0.240%

    No Known Activations