© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "ap-" associated with different contexts, such as medical terms, literature, and political commentary

    oai_token-act-pair · gpt-3.5-turbo

    the term "apologist" and its variations

    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
    IGHTS
    -0.65
     Hurricanes
    -0.63
     consequential
    -0.60
     Carib
    -0.60
     devils
    -0.60
     Jagu
    -0.59
     fry
    -0.59
     injecting
    -0.59
     Vision
    -0.58
     slashing
    -0.57
    POSITIVE LOGITS
    ocry
    1.62
    ocaly
    1.57
    ocalyptic
    1.44
    athetic
    1.44
    olitical
    1.41
    artment
    1.34
    athy
    1.34
    othe
    1.33
    ople
    1.30
    otrop
    1.24
    Activations Density 0.029%

    No Known Activations