© 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. 18537
    Prev
    Next
    INDEX
    Explanations

    instances of phrases introducing a source or reference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that" and its variants 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
    rule
    -0.64
    GY
    -0.61
     dying
    -0.60
    natureconservancy
    -0.59
     downtime
    -0.58
    animate
    -0.57
     retiring
    -0.56
     Favorite
    -0.56
     expectation
    -0.56
    zero
    -0.55
    POSITIVE LOGITS
     summarizes
    1.38
     depicts
    1.36
     outlines
    1.30
     illustrates
    1.25
     contains
    1.23
     discusses
    1.23
     describes
    1.22
     summar
    1.19
     includes
    1.17
     summarize
    1.16
    Activations Density 0.213%

    No Known Activations