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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18617
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to ownership or 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
    oS
    -0.67
    omever
    -0.66
    VI
    -0.65
    vere
    -0.65
    shaw
    -0.64
    Textures
    -0.64
    Ú
    -0.64
    ocument
    -0.63
    vre
    -0.63
    WARD
    -0.63
    POSITIVE LOGITS
     usual
    1.09
     own
    1.02
     seat
    0.94
     hometown
    0.93
     comfort
    0.92
     rightful
    0.91
     customary
    0.91
     cush
    0.90
     barracks
    0.88
     senses
    0.87
    Activations Density 0.118%

    No Known Activations