© 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. 6639
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal and organizational belonging

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inclusion and involvement within various 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
     WATCHED
    -0.65
    BSD
    -0.60
    76561
    -0.59
     (#
    -0.56
    DAQ
    -0.55
     Minotaur
    -0.55
     miser
    -0.54
     thirst
    -0.53
     herein
    -0.53
     whereas
    -0.52
    POSITIVE LOGITS
    animate
    0.84
     workplaces
    0.79
     adjoining
    0.78
     vitro
    0.78
    actions
    0.76
     conferences
    0.76
    ospons
    0.75
     other
    0.75
     classrooms
    0.75
     cafes
    0.74
    Activations Density 0.198%

    No Known Activations