Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22368
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters, specifically involving estates or properties

    oai_token-act-pair · gpt-3.5-turbo

    references to estates, particularly in a legal or financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thia
    -0.95
     Ans
    -0.80
    tics
    -0.69
    izu
    -0.66
    ontent
    -0.65
    tic
    -0.64
    ERO
    -0.62
    OST
    -0.62
    airo
    -0.61
     Bie
    -0.60
    POSITIVE LOGITS
     estate
    0.97
     holdings
    0.93
     Estate
    0.88
     estates
    0.86
     execut
    0.82
     agent
    0.81
     heir
    0.76
    estate
    0.74
     asset
    0.71
     vault
    0.71
    Activations Density 0.018%

    No Known Activations