© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    verbs related to performing actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "do" and its variations in different contexts

    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
    raltar
    -0.69
    rification
    -0.66
    unity
    -0.66
    isu
    -0.65
    éĹĺ
    -0.65
    DOC
    -0.62
    LI
    -0.60
    ESA
    -0.60
    olson
    -0.60
    Attempts
    -0.59
    POSITIVE LOGITS
     chores
    1.10
     laundry
    1.10
     homework
    1.03
     something
    0.96
     things
    0.96
    xx
    0.90
     yoga
    0.90
     anything
    0.90
    ggy
    0.89
    zed
    0.88
    Activations Density 0.105%

    No Known Activations