© 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. 20515
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticizing or condemning various situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decimate" in various contexts

    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
    ĪĴ
    -0.75
     Kenyan
    -0.62
     Jinn
    -0.59
     Hopkins
    -0.59
     Carter
    -0.58
    gers
    -0.57
    WAYS
    -0.57
     tong
    -0.57
     Hearts
    -0.57
     Sabbath
    -0.56
    POSITIVE LOGITS
    rypted
    1.45
    ryption
    1.31
    oded
    1.25
    ried
    1.20
    rying
    1.19
    isions
    1.16
    imating
    1.13
    imated
    1.10
    olon
    1.09
    oder
    1.08
    Activations Density 0.013%

    No Known Activations