© 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. 10-RES-JB
    11. 13944
    Prev
    Next
    INDEX
    Explanations

    terms related to updating, informing, or taking responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to threats and retaliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Entered
    -0.64
     Sina
    -0.60
     Gone
    -0.58
     Illustrated
    -0.57
    pired
    -0.56
    itled
    -0.56
     Exhibition
    -0.53
    Untitled
    -0.52
    Vision
    -0.52
    bered
    -0.52
    POSITIVE LOGITS
     whenever
    1.53
     anytime
    1.46
     whichever
    1.42
     if
    1.35
     wherever
    1.24
     whatever
    1.18
     whoever
    1.16
     accordingly
    1.11
    soever
    1.11
     hereafter
    1.09
    Activations Density 0.531%

    No Known Activations