© 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. 7-RES-JB
    11. 21154
    Prev
    Next
    INDEX
    Explanations

    phrases indicating urgency or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "must" in various capitalization forms, often indicating a sense of obligation or recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.85
    EStreamFrame
    -0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    gdala
    -0.73
     Monument
    -0.65
    vernment
    -0.65
    iency
    -0.64
     æľ
    -0.64
    itarian
    -0.63
    ãĥŃ
    -0.61
    POSITIVE LOGITS
    hew
    0.82
    angs
    0.81
    aches
    0.81
    ARD
    0.77
    ANG
    0.76
    ENSE
    0.75
    ARDS
    0.74
     comply
    0.74
     obey
    0.74
    ache
    0.73
    Activations Density 0.034%

    No Known Activations