© 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. 21878
    Prev
    Next
    INDEX
    Explanations

    concepts related to psychological/emotional regulation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to emotion regulation and social structures

    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
    autions
    -0.72
    osponsors
    -0.71
    charges
    -0.70
    ices
    -0.69
    parency
    -0.69
    psc
    -0.68
    loads
    -0.67
    DERR
    -0.67
     Details
    -0.67
     details
    -0.67
    POSITIVE LOGITS
     monarchy
    1.05
     dynasty
    0.99
     era
    0.97
     aristocracy
    0.96
     universe
    0.96
     civilisation
    0.93
     millennium
    0.90
     cosmos
    0.88
     empire
    0.87
     genre
    0.87
    Activations Density 0.549%

    No Known Activations