© 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. 16641
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "So" that introduce a statement or question

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "So" at the beginning of sentences

    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
    "},"
    -0.65
    taboola
    -0.65
     AAA
    -0.62
     ``(
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    exclusive
    -0.61
    idity
    -0.60
     ''
    -0.59
    ski
    -0.58
    saf
    -0.58
    POSITIVE LOGITS
    bered
    0.98
    oner
    0.97
    oooo
    0.96
    apy
    0.95
    ooo
    0.93
    oths
    0.93
    othes
    0.91
    arin
    0.89
    ppy
    0.85
    FTWARE
    0.84
    Activations Density 0.055%

    No Known Activations