© 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. 34
    Prev
    Next
    INDEX
    Explanations

    references related to motivation or the word "mot" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to motivation and motivational concepts

    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
     complimentary
    -0.66
    theless
    -0.64
     equally
    -0.61
     Border
    -0.61
     Trace
    -0.60
     Artemis
    -0.60
     Veronica
    -0.59
     Clay
    -0.58
     Yankee
    -0.57
     Silence
    -0.57
    POSITIVE LOGITS
    ivation
    1.65
    ivated
    1.64
    ivating
    1.49
    iv
    1.24
    ör
    1.16
    oring
    1.11
    orm
    1.09
    oko
    1.09
    ives
    1.09
    orman
    1.08
    Activations Density 0.031%

    No Known Activations