© 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. 3-RES-JB
    11. 23228
    Prev
    Next
    INDEX
    Explanations

    the letter "Z" followed by a number denoting different variations

    oai_token-act-pair · gpt-3.5-turbo

    the letter "Z" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tenance
    -0.78
     Lauder
    -0.70
    espie
    -0.69
    ãĥ¼ãĥĨ
    -0.68
     Scots
    -0.67
    tainment
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
    FontSize
    -0.64
    otaur
    -0.64
     spirited
    -0.64
    POSITIVE LOGITS
    ERO
    1.22
    ebra
    1.21
    odiac
    1.08
    eros
    1.04
    immer
    0.99
    ones
    0.97
    aku
    0.97
    ooming
    0.97
    ipp
    0.96
    eta
    0.96
    Activations Density 0.020%

    No Known Activations