© 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. 1-RES-JB
    11. 3735
    Prev
    Next
    INDEX
    Explanations

    words related to the term 'boiler'

    oai_token-act-pair · gpt-3.5-turbo

    the term "boilerplate" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĵĺ
    -0.69
    ðĿ
    -0.65
     lifetime
    -0.64
     lifelong
    -0.64
    apest
    -0.63
     particular
    -0.63
     isot
    -0.61
    reme
    -0.60
     unanimous
    -0.59
    alg
    -0.59
    POSITIVE LOGITS
    iler
    0.97
    ilers
    0.79
    mson
    0.78
    ounge
    0.77
    iper
    0.74
    tenance
    0.74
    aceous
    0.73
    throp
    0.73
    tyard
    0.71
    oaded
    0.69
    Activations Density 0.003%

    No Known Activations