© 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. 7-RES-JB
    11. 2253
    Prev
    Next
    INDEX
    Explanations

    words related to different types of centers or facilities

    oai_token-act-pair · gpt-3.5-turbo

    the term "center" or variations thereof, indicating various types of facilities or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.91
    ãĥĥãĥī
    -0.80
    ãĥīãĥ©
    -0.75
    */(
    -0.70
    âĸ¬âĸ¬
    -0.67
    ordan
    -0.66
    à¥
    -0.66
    chrom
    -0.65
    thin
    -0.65
    crop
    -0.64
    POSITIVE LOGITS
    pieces
    0.87
     Plaza
    0.82
     located
    0.79
    stadt
    0.77
     pamph
    0.76
    eous
    0.71
    piece
    0.70
    ologies
    0.70
     staffed
    0.68
    liners
    0.67
    Activations Density 0.032%

    No Known Activations