© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16555
    Prev
    Next
    INDEX
    Explanations

    mentions of nuclear reactors

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hust
    -0.78
     Zac
    -0.77
    arte
    -0.72
     Et
    -0.70
    olo
    -0.66
     sle
    -0.66
     Herm
    -0.66
     Mens
    -0.66
     Hip
    -0.65
    Individual
    -0.64
    POSITIVE LOGITS
     reactor
    3.58
     reactors
    3.39
     Fukushima
    2.00
     plutonium
    1.93
     Nuclear
    1.80
     nuclear
    1.69
     uranium
    1.66
    uclear
    1.59
     radioactive
    1.57
    nuclear
    1.56
    Activations Density 0.036%

    No Known Activations