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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18599
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to geopolitical conflicts or controversies

    oai_token-act-pair · gpt-3.5-turbo

    demonstrative or relative pronouns indicating specific entities or groups

    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
    Returns
    -0.73
    Untitled
    -0.72
    laughs
    -0.68
    uces
    -0.62
     increments
    -0.62
    prints
    -0.61
     stays
    -0.61
    Alright
    -0.61
     wheels
    -0.60
    lyss
    -0.60
    POSITIVE LOGITS
     were
    1.15
     include
    1.04
     have
    1.00
     constitute
    0.99
     are
    0.98
     comprise
    0.96
     weren
    0.94
     violate
    0.94
     allege
    0.93
     dominate
    0.89
    Activations Density 0.200%

    No Known Activations