© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 13605
    Prev
    Next
    INDEX
    Explanations

    social media usernames and links

    oai_token-act-pair · gpt-3.5-turbo

    references to social media interactions, particularly involving Twitter handles and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mort
    -0.67
     ageing
    -0.65
     apart
    -0.65
     dispers
    -0.63
     reven
    -0.63
     boarding
    -0.62
     carpet
    -0.62
     dating
    -0.61
     claw
    -0.59
     outl
    -0.59
    POSITIVE LOGITS
    <|endoftext|>
    1.16
     Alternatively
    1.10
     Follow
    1.02
    tumblr
    0.91
    htm
    0.91
    aspx
    0.91
     Also
    0.90
    php
    0.88
    rss
    0.84
    Copyright
    0.83
    Activations Density 0.046%

    No Known Activations