© 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. 6-RES-JB
    11. 7864
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large amount or increase in activity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large amounts or surges of activity or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.82
    ©¶æ
    -0.71
    nect
    -0.64
    tarians
    -0.63
     Flags
    -0.63
    rongh
    -0.63
     Territory
    -0.63
    rib
    -0.62
     harmless
    -0.62
     Governors
    -0.61
    POSITIVE LOGITS
    tro
    0.89
    pour
    0.89
    azard
    0.76
    storm
    0.76
    DragonMagazine
    0.76
    channelAvailability
    0.74
    astic
    0.73
     barrage
    0.70
     tide
    0.70
     churn
    0.70
    Activations Density 0.116%

    No Known Activations