© 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
    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. 17417
    Prev
    Next
    INDEX
    Explanations

    situations where buildings are described by their number of stories

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of stories in buildings

    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
    ibaba
    -0.85
    netflix
    -0.77
    scientific
    -0.75
    uncture
    -0.75
    Phys
    -0.71
    anco
    -0.69
    cific
    -0.67
     Canaver
    -0.67
    iotic
    -0.67
     Sturgeon
    -0.65
    POSITIVE LOGITS
     balcony
    1.08
     apartment
    1.07
     buildings
    1.03
     apartments
    0.98
     facade
    0.96
     towers
    0.94
     residential
    0.92
     occupancy
    0.92
     skysc
    0.89
     balcon
    0.88
    Activations Density 0.058%

    No Known Activations