© 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. 11-RES-JB
    11. 7582
    Prev
    Next
    INDEX
    Explanations

    phrases related to possessive pronouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns and possessive forms indicating relationships

    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
    ibaba
    -0.76
    icter
    -0.72
    wav
    -0.69
    ruction
    -0.69
    uria
    -0.66
    Loading
    -0.64
    borgh
    -0.64
    abbage
    -0.63
    inventoryQuantity
    -0.63
    izu
    -0.62
    POSITIVE LOGITS
     peers
    1.54
     colleagues
    1.51
     superiors
    1.48
     detractors
    1.47
     followers
    1.43
     contemporaries
    1.41
     counterparts
    1.35
     fellow
    1.34
     constituents
    1.34
     friends
    1.34
    Activations Density 0.187%

    No Known Activations