© 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. 4-RES-JB
    11. 618
    Prev
    Next
    INDEX
    Explanations

    words related to licensing agreements or arrangements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "licensing" and related concepts

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

    No Comments

    Negative Logits
    ilon
    -0.81
     Lans
    -0.76
    orah
    -0.71
    sonian
    -0.70
    dain
    -0.69
    inx
    -0.69
    Discussion
    -0.67
     Cthulhu
    -0.67
    bra
    -0.67
    ilight
    -0.66
    POSITIVE LOGITS
     licensing
    1.16
     licenses
    1.10
    ensing
    0.97
     licences
    0.96
     fees
    0.92
     agreements
    0.88
    license
    0.86
     infringement
    0.83
    Lic
    0.83
    rats
    0.83
    Activations Density 0.014%

    No Known Activations