© 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. 20356
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "do" and its variations in contexts related to actions and responsibilities

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    Rank
    -0.61
     CLS
    -0.59
     Islands
    -0.58
    Cook
    -0.58
     Flood
    -0.56
    mares
    -0.55
     Lank
    -0.55
     ascended
    -0.55
    Used
    -0.55
    POSITIVE LOGITS
     everything
    1.07
    omsday
    1.07
     something
    1.04
    oming
    1.02
    oms
    1.02
     away
    0.98
     nothing
    0.97
    xx
    0.96
     anything
    0.96
     likewise
    0.94
    Activations Density 0.106%

    No Known Activations