© 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. 11479
    Prev
    Next
    INDEX
    Explanations

    words related to objects or actions involving the use of "sil" such as "silenced," "silk," "screener," and more

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "silence" and related terms

    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
    enegger
    -0.72
     damned
    -0.69
    OTAL
    -0.69
    ELS
    -0.69
     Briggs
    -0.65
     Blessed
    -0.65
    eering
    -0.65
    etheless
    -0.65
     Rampage
    -0.62
    ARK
    -0.62
    POSITIVE LOGITS
    encer
    1.46
    encers
    1.45
    encing
    1.39
    enced
    1.34
    icone
    1.25
    ences
    1.19
    icon
    1.10
    icate
    1.07
    hou
    1.05
    ica
    1.04
    Activations Density 0.022%

    No Known Activations