© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 9678
    Prev
    Next
    INDEX
    Explanations

    words related to relaxation or a relaxed state

    oai_token-act-pair · gpt-3.5-turbo

    terms related to relaxation and calming experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    claim
    -0.80
    otyp
    -0.70
    agically
    -0.69
    otype
    -0.67
    ebook
    -0.66
    mal
    -0.65
     Kw
    -0.64
    dat
    -0.64
     serial
    -0.63
     Accounts
    -0.63
    POSITIVE LOGITS
     relax
    3.20
     relaxing
    3.14
     relaxation
    3.01
     relaxed
    2.60
     Relax
    2.34
     lax
    1.69
     loosen
    1.68
     loos
    1.56
     calming
    1.52
     easing
    1.47
    Activations Density 0.040%

    No Known Activations