© 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. 4-RES-JB
    11. 18541
    Prev
    Next
    INDEX
    Explanations

    social media platform names and handles

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms and calls to action for following accounts

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

    No Comments

    Negative Logits
    chwitz
    -0.79
    ornia
    -0.69
    romy
    -0.69
    avorite
    -0.68
    ©¶æ
    -0.68
    ĪĴ
    -0.66
    owship
    -0.65
    AME
    -0.63
    pecting
    -0.63
    Ļ½
    -0.63
    POSITIVE LOGITS
     embed
    0.77
     nort
    0.69
     Telegram
    0.68
     twitter
    0.67
     email
    0.67
    LinkedIn
    0.66
     decentral
    0.66
    ":[
    0.66
     live
    0.63
    Guard
    0.62
    Activations Density 0.087%

    No Known Activations