© 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. 1-RES-JB
    11. 5017
    Prev
    Next
    INDEX
    Explanations

    phrases related to text formatting/icons/emojis

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "âĢ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scatter
    -0.74
     protective
    -0.71
     paternal
    -0.68
     whirlwind
    -0.66
     domestic
    -0.66
    ctors
    -0.64
     target
    -0.64
     detached
    -0.63
     mindset
    -0.63
     bung
    -0.63
    POSITIVE LOGITS
    âĢ
    1.23
    âĢķ
    1.08
    âĢł
    1.05
    âĹ¼
    0.99
    ¯
    0.97
    ¶
    0.96
    âĸº
    0.95
    §
    0.92
    ¹
    0.91
    ––
    0.91
    Activations Density 0.738%

    No Known Activations