© 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. 3-RES-JB
    11. 24494
    Prev
    Next
    INDEX
    Explanations

    verb phrases that express obligation, possibility, or consequence

    oai_token-act-pair · gpt-3.5-turbo

    modal and auxiliary verbs that indicate obligation or necessity

    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
     Ago
    -0.54
     pursu
    -0.51
     Sum
    -0.49
     Vers
    -0.47
     Buk
    -0.47
     Releases
    -0.47
     partnership
    -0.47
     Mak
    -0.47
     Kron
    -0.47
     Kenn
    -0.46
    POSITIVE LOGITS
    rael
    0.70
    senal
    0.70
    Ĥİ
    0.67
    onite
    0.65
     thereby
    0.62
    SourceFile
    0.62
     nevertheless
    0.62
    ŃĶ
    0.62
     hereby
    0.59
    terness
    0.57
    Activations Density 1.409%

    No Known Activations