© 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. 8-RES-JB
    11. 1359
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantity or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or express the extent of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mason
    -0.63
     Dai
    -0.61
     Democr
    -0.58
    heses
    -0.57
    oller
    -0.56
     Cantor
    -0.56
     respir
    -0.54
    ASED
    -0.54
    ãģ®å®
    -0.54
     Fridays
    -0.54
    POSITIVE LOGITS
    pired
    1.23
    pires
    1.18
    ynchron
    1.15
    phy
    1.09
    piration
    1.06
    ocial
    0.97
    ym
    0.95
    part
    0.93
    pire
    0.93
    phalt
    0.92
    Activations Density 0.105%

    No Known Activations