© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 892
    Prev
    Next
    INDEX
    Explanations

    references to some name or username containing the letters "dd" at the start or middle of the word

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "edit" or "editing."

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

    No Comments

    Negative Logits
    hazard
    -0.76
    flu
    -0.70
    CLE
    -0.67
     Stras
    -0.67
    GROUND
    -0.66
     Crimean
    -0.64
    involved
    -0.64
    helle
    -0.63
     MIA
    -0.63
    riors
    -0.61
    POSITIVE LOGITS
    ragon
    1.16
    ed
    0.97
    dd
    0.97
    orf
    0.92
    itional
    0.91
    umbs
    0.90
    ressing
    0.89
    iamond
    0.88
    aughter
    0.87
    ouble
    0.86
    Activations Density 0.008%

    No Known Activations