© 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. 5380
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by a number or a noun

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns referring to individuals or entities

    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
     Metatron
    -0.65
     Amen
    -0.63
     Gutenberg
    -0.62
     Kers
    -0.59
     Exception
    -0.56
    jac
    -0.55
     circulation
    -0.55
     exception
    -0.54
     gag
    -0.54
     Papers
    -0.53
    POSITIVE LOGITS
     own
    1.17
     respective
    1.14
     peers
    1.08
     country
    1.06
     hometown
    1.01
    idency
    0.93
     surroundings
    0.89
     contemporaries
    0.89
    panic
    0.88
     namesake
    0.87
    Activations Density 0.195%

    No Known Activations