© 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. 2-RES-JB
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    tweets from social media

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media interactions, particularly tweets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.79
    ccording
    -0.70
    undai
    -0.69
     mids
    -0.67
    ologne
    -0.67
    «ĺ
    -0.65
    rift
    -0.64
    sbm
    -0.64
    NetMessage
    -0.64
    haust
    -0.63
    POSITIVE LOGITS
     Tweet
    1.22
    edin
    1.00
    Tweet
    0.98
    deck
    0.97
     Emails
    0.90
    storms
    0.84
    weet
    0.81
    storm
    0.78
     Username
    0.77
    Chat
    0.76
    Activations Density 0.002%

    No Known Activations