© 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. 11-RES-JB
    6. 6563
    Prev
    Next
    INDEX
    Explanations

    phrases related to anticipating something or looking forward to it

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to anticipation or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ËĪ
    -0.69
    emale
    -0.69
    avez
    -0.61
    xtap
    -0.61
     ·
    -0.59
    ortium
    -0.56
    wcs
    -0.54
    ensibly
    -0.51
    ¶ħ
    -0.51
    interstitial
    -0.50
    POSITIVE LOGITS
    )."
    2.38
    ."
    2.32
    .")
    2.30
    ),"
    2.21
    ".
    2.06
    ."[
    2.04
    .,"
    2.01
    .""
    1.96
    .'"
    1.95
    ]."
    1.94
    Activations Density 1.595%

    No Known Activations