© 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. 3-RES-JB
    11. 662
    Prev
    Next
    INDEX
    Explanations

    words related to a strong force or energy that is building or increasing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to momentum or progress in various contexts

    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
    tein
    -0.90
    Interstitial
    -0.87
    ramid
    -0.71
    hiba
    -0.70
    bery
    -0.68
    han
    -0.66
    sys
    -0.66
    mberg
    -0.65
     dearly
    -0.65
    olla
    -0.64
    POSITIVE LOGITS
     momentum
    1.11
    wcs
    0.81
    ernaut
    0.75
    ulse
    0.74
     impetus
    0.71
    itri
    0.70
     consolidation
    0.68
     inertia
    0.67
    olicy
    0.66
    icity
    0.65
    Activations Density 0.019%

    No Known Activations