© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 17380
    Prev
    Next
    INDEX
    Explanations

    details about facilities, such as their descriptions, locations, operations, and inspections

    oai_token-act-pair · gpt-3.5-turbo

    references to facilities and their attributes

    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
    uscript
    -0.78
    sen
    -0.76
    thin
    -0.73
    plets
    -0.72
    jin
    -0.69
    lihood
    -0.69
    poll
    -0.68
    hood
    -0.68
    tail
    -0.67
    chrom
    -0.67
    POSITIVE LOGITS
     facilities
    0.97
     facility
    0.86
     renovations
    0.86
     Facilities
    0.81
     utilization
    0.78
     Facility
    0.77
     premises
    0.77
     rentals
    0.76
     attendants
    0.75
    ility
    0.73
    Activations Density 0.016%

    No Known Activations