Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 421
    Prev
    Next
    INDEX
    Explanations

    words associated with droughts

    oai_token-act-pair · gpt-4-turbo

    phrases related to natural disasters and extreme weather events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to natural disasters and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kus
    -0.79
     Wong
    -0.72
    Und
    -0.72
    NT
    -0.69
     VID
    -0.68
    Pixel
    -0.68
     LIMITED
    -0.67
    atin
    -0.67
    POS
    -0.66
     Vec
    -0.66
    POSITIVE LOGITS
     advis
    1.06
     runoff
    0.98
     rains
    0.89
     forecasts
    0.88
     forecast
    0.85
     havoc
    0.84
     storms
    0.81
     showers
    0.81
     inund
    0.79
    hower
    0.78
    Activations Density 0.187%

    No Known Activations