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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5788
    Prev
    Next
    INDEX
    Explanations

    mentions of condominiums in a real estate context

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to condominiums and housing types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Published
    -0.73
    saf
    -0.71
    mus
    -0.71
    mp
    -0.68
    ker
    -0.67
    ym
    -0.67
    pid
    -0.67
    sen
    -0.66
    zee
    -0.66
     Shakespeare
    -0.65
    POSITIVE LOGITS
     condo
    1.34
     condos
    1.27
    ominium
    1.11
     apartments
    0.93
     neighb
    0.87
     rentals
    0.86
     apartment
    0.83
     occupancy
    0.83
    rete
    0.81
     rental
    0.80
    Activations Density 0.006%

    No Known Activations