© 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. 2-RES-JB
    11. 5979
    Prev
    Next
    INDEX
    Explanations

    a peculiar mix of characters and languages, potentially related to coding or encrypted messages

    oai_token-act-pair · gpt-3.5-turbo

    Arabic script or characters

    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
    iko
    -0.91
    onge
    -0.89
    psey
    -0.80
    ellen
    -0.80
    ipel
    -0.80
    erton
    -0.75
    eson
    -0.75
    idges
    -0.74
    upiter
    -0.73
    tten
    -0.73
    POSITIVE LOGITS
    د
    1.61
    Ù
    1.61
    ÙĨ
    1.58
    ا
    1.53
    Ùĩ
    1.52
    اØ
    1.47
    س
    1.46
    ت
    1.46
    ب
    1.43
    Ùħ
    1.42
    Activations Density 0.002%

    No Known Activations