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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 4138
    Prev
    Next
    INDEX
    Explanations

    pronouns, possessive pronouns, and possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olkien
    -0.86
    adobe
    -0.78
    south
    -0.77
    arios
    -0.76
    wrap
    -0.74
    osate
    -0.72
    urch
    -0.71
    alyst
    -0.70
    needed
    -0.70
    western
    -0.70
    POSITIVE LOGITS
     name
    1.03
     majesty
    1.01
     guts
    1.00
     strengths
    0.99
     Majesty
    0.97
     corpse
    0.95
     weaknesses
    0.94
     birthday
    0.91
     plight
    0.90
     names
    0.89
    Activations Density 0.345%

    No Known Activations