© 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. 8-RES-JB
    11. 7819
    Prev
    Next
    INDEX
    Explanations

    words related to names or titles that end in "mon"

    oai_token-act-pair · gpt-3.5-turbo

    words related to ceremonial or ritualistic occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Norn
    -0.73
    FUL
    -0.64
     Paste
    -0.64
    EMP
    -0.64
    NRS
    -0.64
    unta
    -0.61
    ENG
    -0.61
    ACTED
    -0.60
    RED
    -0.59
     Prescott
    -0.59
    POSITIVE LOGITS
    strous
    1.12
    itored
    1.10
    etary
    1.06
    ial
    1.03
    ials
    0.96
    uclear
    0.92
    ths
    0.92
    astery
    0.91
    iac
    0.91
    stros
    0.87
    Activations Density 0.025%

    No Known Activations