© 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. 4-RES-JB
    6. 10648
    Prev
    Next
    INDEX
    Explanations

    words related to shipping, arrival, or release dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the shipping and arrival of products or releases

    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
    column
    -0.75
    asper
    -0.72
    arre
    -0.72
    eric
    -0.69
     Administ
    -0.67
    fur
    -0.65
    lig
    -0.65
     Pse
    -0.65
    productive
    -0.65
    othe
    -0.64
    POSITIVE LOGITS
     unveil
    0.91
     announcements
    0.89
     debuted
    0.88
    atform
    0.88
     debut
    0.85
     unveiling
    0.85
     rollout
    0.83
    Tomorrow
    0.82
     announcement
    0.82
     unveiled
    0.80
    Activations Density 0.458%

    No Known Activations