© 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. 10-RES-JB
    11. 11611
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth and expansion

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of expansion in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akia
    -0.78
    «
    -0.73
    oka
    -0.72
    MET
    -0.66
    itsu
    -0.66
    âķIJâķIJ
    -0.65
    puter
    -0.64
    rol
    -0.64
    mir
    -0.63
    ppe
    -0.63
    POSITIVE LOGITS
    ansion
    1.12
    ary
    1.00
    ist
    0.95
    arily
    0.91
    ism
    0.88
    naires
    0.80
    ivist
    0.79
     pains
    0.78
    oing
    0.78
     expansion
    0.77
    Activations Density 0.053%

    No Known Activations