Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16072
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining calmness or peacefulness

    oai_token-act-pair · gpt-3.5-turbo

    references to a sense of calmness or tranquility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographies
    -0.75
    hester
    -0.73
    OGR
    -0.72
    rocket
    -0.69
    ammy
    -0.69
    fruit
    -0.65
    ADA
    -0.64
    iosyncr
    -0.64
     Sins
    -0.63
     Parenthood
    -0.63
    POSITIVE LOGITS
     calm
    1.06
    ness
    0.97
     demeanor
    0.90
    erate
    0.85
    est
    0.82
    escal
    0.81
     calming
    0.79
     Calm
    0.77
     partName
    0.77
    zers
    0.77
    Activations Density 0.016%

    No Known Activations