© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 12062
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "holder" or "holders," often in the context of ownership or possession

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that hold ownership or rights to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.73
    oco
    -0.72
    ologist
    -0.72
    eller
    -0.70
    inx
    -0.68
    romy
    -0.68
    clusions
    -0.68
    okin
    -0.66
    enic
    -0.66
    ebook
    -0.65
    POSITIVE LOGITS
    holders
    1.30
    holder
    1.17
     holders
    0.97
     holder
    0.87
    pring
    0.85
    holding
    0.78
    houses
    0.77
    pole
    0.77
    iture
    0.75
    hips
    0.73
    Activations Density 0.035%

    No Known Activations