© 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. 9-RES-JB
    11. 15603
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns followed by possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual's work or identity

    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
    osate
    -0.95
    needed
    -0.82
    microsoft
    -0.80
    jury
    -0.79
    uve
    -0.73
    urers
    -0.72
    ATA
    -0.72
    obe
    -0.69
    livion
    -0.69
    ibraries
    -0.69
    POSITIVE LOGITS
     antics
    1.22
     penchant
    1.14
     adventures
    1.09
     hilarious
    1.03
     backstory
    1.03
     thoughts
    1.03
     adorable
    1.02
     newest
    1.00
     latest
    0.99
     tweets
    0.98
    Activations Density 0.260%

    No Known Activations