© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    titles or phrases starting with "A"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of titles that begin with "A" followed by any subject

    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
     extent
    -0.76
     infringement
    -0.72
     annex
    -0.72
     affordability
    -0.72
     embargo
    -0.71
     interstate
    -0.71
     proxies
    -0.71
     imaging
    -0.70
     anchor
    -0.70
     exemptions
    -0.69
    POSITIVE LOGITS
     Brief
    1.10
     Conversation
    1.06
     Taste
    1.02
     Thousand
    1.02
     Tale
    1.00
    perture
    1.00
     Monstrous
    0.99
     Dangerous
    0.99
     Gentleman
    0.99
     Matter
    0.97
    Activations Density 0.061%

    No Known Activations