© 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. 4-RES-JB
    11. 7488
    Prev
    Next
    INDEX
    Explanations

    phrases related to relaxation and leisure activities

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to relaxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nic
    -0.68
     Golem
    -0.64
     Canary
    -0.62
     Hole
    -0.62
    fab
    -0.62
     Antar
    -0.60
    iop
    -0.60
    race
    -0.58
     Sins
    -0.58
    */(
    -0.57
    POSITIVE LOGITS
     relax
    0.94
     Relax
    0.93
     relaxation
    0.93
     relaxing
    0.88
    atorium
    0.78
    bnb
    0.76
     relaxed
    0.75
    ADRA
    0.74
    ESCO
    0.74
    isse
    0.74
    Activations Density 0.012%

    No Known Activations