© 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. 2-RES-JB
    11. 17675
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to relaxation or a relaxed state

    oai_token-act-pair · gpt-3.5-turbo

    expressions and synonyms related to relaxation and comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mortal
    -0.66
    iop
    -0.64
    hner
    -0.62
     Presidency
    -0.61
     Shogun
    -0.61
    race
    -0.60
    apter
    -0.60
    yes
    -0.59
    Ranked
    -0.59
    lay
    -0.59
    POSITIVE LOGITS
     relaxed
    1.02
     relaxation
    1.02
     relax
    1.01
     relaxing
    0.95
     Relax
    0.93
     easing
    0.85
     loosen
    0.78
    terness
    0.77
    bnb
    0.74
    glers
    0.73
    Activations Density 0.015%

    No Known Activations