© 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. 11107
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or controversies

    oai_token-act-pair · gpt-3.5-turbo

    references to events occurring after significant incidents

    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
    à©
    -0.82
    cking
    -0.78
    à¨
    -0.78
    ////////////////////////////////
    -0.76
    utical
    -0.74
    oir
    -0.72
    ELY
    -0.71
    ript
    -0.70
    çī
    -0.70
    ItemThumbnailImage
    -0.69
    POSITIVE LOGITS
     revelations
    1.33
     allegations
    1.01
     Hurricane
    1.01
     Wikileaks
    1.00
     reports
    0.96
     WikiLeaks
    0.96
     disclosures
    0.95
     scandals
    0.94
     announcing
    0.93
     leaked
    0.93
    Activations Density 0.223%

    No Known Activations