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. 6-RES-JB
    6. 19480
    Prev
    Next
    INDEX
    Explanations

    places or spaces that can accommodate large groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to capacity or accommodation in various contexts, particularly related to seating, facilities, and populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.79
     reprim
    -0.75
    rom
    -0.68
    utan
    -0.68
     dishon
    -0.66
     tread
    -0.66
     immobil
    -0.65
    hog
    -0.64
    robe
    -0.64
     Skydragon
    -0.63
    POSITIVE LOGITS
     capacity
    1.03
    population
    0.93
     Capacity
    0.91
     manpower
    0.91
     vacancies
    0.89
    Population
    0.88
     capacities
    0.87
    capacity
    0.85
     population
    0.83
     influx
    0.83
    Activations Density 0.841%

    No Known Activations