© 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. 3-RES-JB
    11. 5034
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters, especially those related to estates and inheritance

    oai_token-act-pair · gpt-3.5-turbo

    references to estates and property management issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thia
    -0.95
     Ans
    -0.80
    OST
    -0.71
     Fas
    -0.65
    annels
    -0.63
    auts
    -0.63
     Logic
    -0.62
    ERO
    -0.62
    OSE
    -0.62
    ost
    -0.62
    POSITIVE LOGITS
     estates
    1.02
     estate
    1.01
     Estate
    0.89
     execut
    0.86
     holdings
    0.83
     heir
    0.81
     agent
    0.76
    chool
    0.75
    estate
    0.74
    folio
    0.73
    Activations Density 0.017%

    No Known Activations