© 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. 2-RES-JB
    6. 17593
    Prev
    Next
    INDEX
    Explanations

    proper nouns or entities written in all capital letters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ON."

    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
    ãĤ±
    -0.82
    Ĥª
    -0.73
    utenberg
    -0.72
    ãĤ§
    -0.70
    ãĤ©
    -0.69
    ãĥ¼ãĥ³
    -0.69
    ãĥĥ
    -0.68
     Wolfe
    -0.68
    ãĤ¶
    -0.67
    ãĤ¢ãĥ«
    -0.67
    POSITIVE LOGITS
    etheless
    1.19
    LY
    1.08
    ON
    1.03
    LINE
    0.98
    AUT
    0.94
    ONS
    0.86
    CE
    0.84
    ELY
    0.83
    IUM
    0.82
    ucle
    0.81
    Activations Density 0.008%

    No Known Activations