© 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. 4-RES-JB
    11. 11165
    Prev
    Next
    INDEX
    Explanations

    abbreviations where "LE" is at the end and they seem to be related to various fields or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "LE" and closely related phrases

    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
    ãĥ¼ãĥĨãĤ£
    -0.88
    ãĤ¢ãĥ«
    -0.86
    ãĤ±
    -0.84
    ichick
    -0.79
    udeb
    -0.79
    raints
    -0.77
    ãĥĥ
    -0.77
    ilities
    -0.77
    orial
    -0.76
    ctrl
    -0.76
    POSITIVE LOGITS
    VEL
    1.04
    IGH
    0.99
    LE
    0.95
    WOOD
    0.84
    VEN
    0.84
    LOAD
    0.83
    ASE
    0.81
    lla
    0.81
    VAL
    0.80
    TON
    0.80
    Activations Density 0.011%

    No Known Activations