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. 6376
    Prev
    Next
    INDEX
    Explanations

    references to the concept of homeownership

    oai_token-act-pair · gpt-3.5-turbo

    references to homeowners and homeownership-related topics

    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
    bsp
    -0.79
     Virus
    -0.70
     Janeiro
    -0.69
    xon
    -0.66
    olon
    -0.63
     Machine
    -0.63
    Translation
    -0.63
    eming
    -0.62
    OTUS
    -0.61
    ceed
    -0.61
    POSITIVE LOGITS
    hip
    1.13
     homeowners
    0.95
    chool
    0.86
     associations
    0.83
    owners
    0.83
     homeowner
    0.81
     association
    0.72
     tenancy
    0.71
    alty
    0.70
    folk
    0.70
    Activations Density 0.022%

    No Known Activations