© 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. 23895
    Prev
    Next
    INDEX
    Explanations

    phrases related to interspersing or interweaving different elements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "sp" within the text

    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
    ĪĴ
    -0.78
    ãĥĥãĥĪ
    -0.70
    vironment
    -0.67
    assetsadobe
    -0.65
     behold
    -0.64
    obyl
    -0.63
    WAYS
    -0.63
    naissance
    -0.62
     STATES
    -0.61
     sneaking
    -0.61
    POSITIVE LOGITS
    iral
    0.97
    iegel
    0.90
    orp
    0.90
    acer
    0.89
    aghetti
    0.87
    atial
    0.86
    acious
    0.85
    okes
    0.84
    atz
    0.83
    its
    0.83
    Activations Density 0.012%

    No Known Activations