© 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. 17288
    Prev
    Next
    INDEX
    Explanations

    words related to calmness and tranquility

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quiet" and its variations

    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
    ANA
    -0.82
    lete
    -0.76
    cko
    -0.69
    annis
    -0.68
    uana
    -0.68
    issors
    -0.68
    ZI
    -0.67
    rers
    -0.66
    ARK
    -0.65
    okemon
    -0.65
    POSITIVE LOGITS
     quiet
    1.01
    quiet
    0.94
     Quiet
    0.92
     quieter
    0.91
    etooth
    0.78
     partName
    0.77
    edIn
    0.74
    pmwiki
    0.74
     cul
    0.72
    est
    0.72
    Activations Density 0.007%

    No Known Activations