© 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. 23174
    Prev
    Next
    INDEX
    Explanations

    references to specific groups, organizations, and authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to government and community involvement in addressing issues

    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
    uces
    -0.95
    tains
    -0.75
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
     Kills
    -0.68
     Learns
    -0.65
    tained
    -0.65
    uced
    -0.63
     establishes
    -0.62
    ipedia
    -0.61
    aughs
    -0.61
    POSITIVE LOGITS
     are
    1.44
     aren
    1.25
     have
    1.20
    're
    1.11
     intend
    1.11
     haven
    1.11
    have
    1.09
     seem
    1.09
     ARE
    1.07
     HAVE
    0.99
    Activations Density 0.655%

    No Known Activations