© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7752
    Prev
    Next
    INDEX
    Explanations

    searches related to "Snapchat" and mentions "heed" frequently

    oai_token-act-pair · gpt-3.5-turbo

    mentions of key figures and references to chat applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coli
    -0.74
     cur
    -0.71
     gard
    -0.71
    icol
    -0.67
     Ulster
    -0.63
     estates
    -0.63
     grounds
    -0.62
     Gy
    -0.62
     manga
    -0.62
     NIC
    -0.62
    POSITIVE LOGITS
    heed
    3.34
    chat
    2.46
    Chat
    1.29
    CHAT
    1.13
    het
    1.04
    plet
    0.94
    DT
    0.91
     Weber
    0.88
    etooth
    0.88
    quit
    0.88
    Activations Density 0.025%

    No Known Activations