© 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. 6-RES-JB
    11. 16818
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns that indicate ownership or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usp
    -0.69
    clair
    -0.69
    odcast
    -0.65
    omew
    -0.64
    epad
    -0.63
    trak
    -0.62
    apa
    -0.61
     Transfer
    -0.61
     Einstein
    -0.60
    Reviewer
    -0.59
    POSITIVE LOGITS
    ordinary
    0.82
     belongings
    0.77
     imaginable
    0.77
     endeav
    0.75
    together
    0.74
     own
    0.73
     dealings
    0.72
     facets
    0.71
     endeavors
    0.69
     earthly
    0.69
    Activations Density 0.036%

    No Known Activations