© 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. 9-RES-JB
    11. 9987
    Prev
    Next
    INDEX
    Explanations

    phrases related to small and medium-sized entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing small and medium-sized entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.82
    ortmund
    -0.76
    cape
    -0.75
    ilogy
    -0.75
    itect
    -0.75
    Occup
    -0.73
    andise
    -0.70
    terday
    -0.69
    aeda
    -0.68
    Ö¼
    -0.67
    POSITIVE LOGITS
     insignificant
    1.11
     harmless
    1.07
     inexpensive
    1.01
     clumsy
    0.99
     inefficient
    0.98
     fleeting
    0.98
     brittle
    0.94
     timid
    0.93
     ineffective
    0.93
     incremental
    0.92
    Activations Density 0.180%

    No Known Activations