© 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. 20913
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or obligation

    oai_token-act-pair · gpt-3.5-turbo

    imperative verb phrases indicating 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
    vironment
    -0.71
     Laden
    -0.65
    vertisements
    -0.65
    gdala
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     Hamp
    -0.61
    foreseen
    -0.61
    iency
    -0.60
    versions
    -0.60
    lot
    -0.59
    POSITIVE LOGITS
     obey
    0.98
     be
    0.91
     abide
    0.88
     reproduce
    0.88
     surely
    0.87
     comply
    0.82
     therefore
    0.77
     encl
    0.76
     unavoid
    0.75
     preferably
    0.75
    Activations Density 0.028%

    No Known Activations