© 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. 9-RES-JB
    11. 16012
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate preparation or setup

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to preparation or positioning for future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sake
    -0.61
     Pastebin
    -0.60
     simplicity
    -0.59
     abstraction
    -0.58
    loss
    -0.57
     cultured
    -0.56
    tein
    -0.55
     denomin
    -0.55
     deduct
    -0.52
     mentioning
    -0.52
    POSITIVE LOGITS
    for
    0.84
     for
    0.84
    entin
    0.77
    Ready
    0.75
     toward
    0.75
    ombo
    0.75
    eele
    0.74
    Against
    0.73
    GGGGGGGG
    0.73
    For
    0.73
    Activations Density 0.284%

    No Known Activations