© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16151
    Prev
    Next
    INDEX
    Explanations

    words related to tension and stress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tension" and related contexts describing stress or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.77
    glas
    -0.76
    haps
    -0.70
    umption
    -0.68
    prints
    -0.67
    sure
    -0.65
    odes
    -0.65
    igor
    -0.64
    umer
    -0.64
    owers
    -0.64
    POSITIVE LOGITS
     tension
    1.07
     reliever
    0.83
    lessly
    0.80
    uality
    0.80
     Vaugh
    0.73
     pneum
    0.72
    naire
    0.72
     Duo
    0.71
    yip
    0.70
     Gau
    0.70
    Activations Density 0.011%

    No Known Activations