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. 15795
    Prev
    Next
    INDEX
    Explanations

    information related to weather conditions, such as rain, wind, snow, and pressure

    oai_token-act-pair · gpt-3.5-turbo

    references to weather conditions and their impacts

    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
    aughs
    -0.85
    ħĭ
    -0.81
    ģĸ
    -0.80
    chool
    -0.79
    ij士
    -0.78
    legate
    -0.76
     Unch
    -0.74
    Own
    -0.74
    Parents
    -0.74
    Student
    -0.73
    POSITIVE LOGITS
     humidity
    1.52
     moisture
    1.24
     haze
    1.23
     rain
    1.20
     rainfall
    1.16
     rains
    1.14
     ozone
    1.14
     minerals
    1.13
     sunlight
    1.10
     heat
    1.09
    Activations Density 0.384%

    No Known Activations