© 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. 8-RES-JB
    11. 4277
    Prev
    Next
    INDEX
    Explanations

    words related to property or ownership

    oai_token-act-pair · gpt-3.5-turbo

    mentions of property and property ownership issues

    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
    ACTED
    -0.75
    ature
    -0.67
    atures
    -0.65
    arios
    -0.64
     Dj
    -0.63
    ansen
    -0.63
    ²¾
    -0.62
    emonic
    -0.62
    ursday
    -0.62
     Orche
    -0.61
    POSITIVE LOGITS
    owner
    1.19
     owners
    1.11
    owners
    1.06
     owner
    1.05
     Owners
    0.96
     ownership
    0.94
     Owner
    0.87
     holdings
    0.86
    Property
    0.86
     rights
    0.84
    Activations Density 0.033%

    No Known Activations