© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20902
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating or owning something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or ownership related to personal creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.73
    ĸļ
    -0.69
    teness
    -0.65
    ocument
    -0.65
    noon
    -0.60
    train
    -0.60
     âĢº
    -0.59
    thood
    -0.58
    hari
    -0.58
    Prev
    -0.55
    POSITIVE LOGITS
     own
    2.49
     OWN
    1.78
     Own
    1.77
    own
    1.18
    selves
    1.10
    self
    1.00
    Own
    0.89
     desired
    0.86
     first
    0.86
     respective
    0.85
    Activations Density 0.157%

    No Known Activations