© 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. 7671
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and policies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    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
     whilst
    -0.99
     Whilst
    -0.83
    Joined
    -0.76
    Ò
    -0.76
    ilst
    -0.75
    ↵Âł
    -0.74
    Scotland
    -0.72
    beard
    -0.71
    Captain
    -0.70
     Firstly
    -0.70
    POSITIVE LOGITS
     feds
    1.41
     agency
    1.24
     bureau
    1.10
     rollout
    1.04
     administration
    1.02
    oret
    1.01
     backlog
    1.00
     deadline
    1.00
     program
    0.99
     guidelines
    0.98
    Activations Density 0.355%

    No Known Activations