© 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. 11-RES-JB
    11. 10177
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns related to having a strong influence or impact

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Announce
    -0.70
     Loading
    -0.70
     Saying
    -0.67
     Quote
    -0.66
     Recap
    -0.65
     Explain
    -0.65
    OOL
    -0.63
     Conclusion
    -0.63
     adds
    -0.60
     opener
    -0.60
    POSITIVE LOGITS
     been
    1.19
     arisen
    1.12
     hitherto
    1.05
     risen
    1.03
     resided
    1.00
    been
    1.00
     helped
    0.98
     sprung
    0.98
     existed
    0.96
     plagued
    0.94
    Activations Density 0.169%

    No Known Activations