© 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. 0-RES-JB
    6. 11946
    Prev
    Next
    INDEX
    Explanations

    pronouns referencing a possession or belonging

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or ownership, particularly emphasizing the concept of "ours" compared to "theirs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Introduced
    -0.61
    ess
    -0.59
    he
    -0.59
    uru
    -0.58
    fd
    -0.51
    lees
    -0.51
    ik
    -0.50
    Expl
    -0.50
    az
    -0.50
     [+
    -0.49
    POSITIVE LOGITS
     ours
    4.49
     theirs
    2.88
     hers
    2.60
     yours
    2.46
     mine
    2.35
     ourselves
    1.50
     our
    1.39
     OUR
    1.34
     Mine
    1.24
    Our
    1.20
    Activations Density 0.003%

    No Known Activations