© 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. 2-RES-JB
    11. 12683
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensations or states, such as dizziness, intoxication, nausea, exhilaration, and euphoria

    oai_token-act-pair · gpt-3.5-turbo

    words related to dizziness and disorientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.79
    culture
    -0.69
    ger
    -0.68
    CHAT
    -0.68
    WT
    -0.67
    husband
    -0.62
    OF
    -0.62
    PLA
    -0.62
    FER
    -0.61
    LEASE
    -0.61
    POSITIVE LOGITS
     dizz
    1.10
    ingly
    0.91
    ewater
    0.91
    arus
    0.83
    osis
    0.82
    icular
    0.79
    uously
    0.74
    enburg
    0.73
     nause
    0.72
    iest
    0.72
    Activations Density 0.012%

    No Known Activations