© 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. 9-RES-JB
    6. 9988
    Prev
    Next
    INDEX
    Explanations

    words related to individuals such as names, pronouns, and possessives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.73
    icipated
    -0.71
    Scroll
    -0.66
    pleted
    -0.65
     Supports
    -0.64
    imentary
    -0.62
    ounter
    -0.62
    ð
    -0.62
     Additional
    -0.61
    ESE
    -0.61
    POSITIVE LOGITS
     certainly
    1.29
     undeniably
    1.14
     indeed
    1.13
     definitely
    1.07
     hardly
    1.07
     undoubtedly
    1.06
     surely
    1.03
     obviously
    1.02
     notoriously
    1.00
     ALWAYS
    1.00
    Activations Density 0.490%

    No Known Activations