© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23768
    Prev
    Next
    INDEX
    Explanations

    the "|endoftext|" token, particularly when it is part of a transition from one theme to another

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their contextual relevance

    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
     favor
    -1.06
     color
    -1.05
     colored
    -1.05
     colors
    -1.04
     traveling
    -1.04
     favorably
    -1.03
     flavor
    -1.02
     harbor
    -1.00
     favoring
    -0.99
     coloring
    -0.99
    POSITIVE LOGITS
    Labour
    1.98
    BBC
    1.95
    Britain
    1.94
    Scotland
    1.91
    Shape
    1.91
    £
    1.86
    Facebook
    1.78
    Brexit
    1.77
    British
    1.76
    England
    1.72
    Activations Density 0.350%

    No Known Activations