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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 21426
    Prev
    Next
    INDEX
    Explanations

    phrases related to weather and climate

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to weather and climate conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shares
    -0.80
    Queue
    -0.78
    Library
    -0.72
    CHA
    -0.72
    allion
    -0.70
    Lear
    -0.70
     duplication
    -0.69
    library
    -0.69
    YN
    -0.68
    berus
    -0.68
    POSITIVE LOGITS
     temperatures
    1.54
     weather
    1.42
     winters
    1.41
     climates
    1.34
     humidity
    1.31
     conditions
    1.22
     rainy
    1.21
     summers
    1.19
     rains
    1.17
     humid
    1.16
    Activations Density 0.296%

    No Known Activations