© 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. 542
    Prev
    Next
    INDEX
    Explanations

    words that start with the letters "gl"

    oai_token-act-pair · gpt-4-turbo

    phrases related to glitz and glamour

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "gl" in various contexts

    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
    cles
    -0.92
    TAIN
    -0.90
    hyde
    -0.89
    ÄŁ
    -0.82
    CHO
    -0.74
    ItemTracker
    -0.74
    NAS
    -0.74
    ÃįÃį
    -0.70
    OLOGY
    -0.69
    DragonMagazine
    -0.68
    POSITIVE LOGITS
    itz
    1.01
    amping
    0.91
    imm
    0.88
     gl
    0.87
    immer
    0.86
    adiator
    0.83
    ib
    0.82
    itter
    0.79
    ancing
    0.79
    uten
    0.77
    Activations Density 0.005%

    No Known Activations