© 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 EvalsExportsinterp-engineNEWAPI 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. 23021
    Prev
    Next
    INDEX
    Explanations

    instances of situations or events with important implications or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to challenges and their impacts

    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
    tein
    -0.72
     Later
    -0.64
    cell
    -0.63
    ilty
    -0.60
    externalActionCode
    -0.60
    tenance
    -0.58
    ille
    -0.57
    lat
    -0.57
    hesion
    -0.55
    leaf
    -0.55
    POSITIVE LOGITS
     innumerable
    1.07
     plenty
    1.03
     countless
    0.99
     tremendous
    0.98
     unprecedented
    0.98
     considerable
    0.97
     numerous
    0.96
     unparalleled
    0.93
     myriad
    0.93
     ample
    0.91
    Activations Density 0.502%

    No Known Activations