© 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. 20624
    Prev
    Next
    INDEX
    Explanations

    Twitter links with a string representation of a Twitter.com link

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    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
     oun
    -0.94
    ortunately
    -0.89
    senal
    -0.88
     practition
    -0.88
     eleph
    -0.87
    Þ
    -0.85
    ò
    -0.84
     pione
    -0.79
    oreAnd
    -0.79
     exha
    -0.78
    POSITIVE LOGITS
    com
    1.43
    tumblr
    1.01
    wordpress
    1.01
    org
    1.00
    blogspot
    1.00
    COM
    0.96
    twitch
    0.95
    edu
    0.94
    twitter
    0.93
    github
    0.90
    Activations Density 0.018%

    No Known Activations