© 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. 11-RES-JB
    11. 1864
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or strong negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decimate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favourites
    -0.73
     favorites
    -0.64
    ĪĴ
    -0.63
     Kenyan
    -0.62
     priv
    -0.59
     respect
    -0.58
     Kingdom
    -0.58
     bargain
    -0.58
     tong
    -0.58
     await
    -0.57
    POSITIVE LOGITS
    rypted
    1.43
    oded
    1.41
    ryption
    1.34
    rying
    1.32
    olon
    1.29
    ried
    1.28
    imating
    1.26
    imated
    1.23
    ayed
    1.21
    imation
    1.19
    Activations Density 0.018%

    No Known Activations