© 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. 7-RES-JB
    11. 24061
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns such as "their" and "own"

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vine
    -0.95
     Unsure
    -0.86
     Flan
    -0.72
    ozy
    -0.69
    leaf
    -0.68
    ctor
    -0.68
    bender
    -0.67
    uph
    -0.67
    epad
    -0.67
    atoon
    -0.66
    POSITIVE LOGITS
     own
    1.81
     respective
    1.63
    selves
    1.51
     selves
    1.35
     counterparts
    1.23
     careers
    1.22
     minds
    1.21
     hearts
    1.20
     lives
    1.19
     OWN
    1.14
    Activations Density 0.219%

    No Known Activations