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. 7-RES-JB
    6. 10253
    Prev
    Next
    INDEX
    Explanations

    natural disaster names, particularly hurricanes

    oai_token-act-pair · gpt-3.5-turbo

    references to hurricanes and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skirts
    -1.11
    ells
    -0.91
    unal
    -0.81
    ando
    -0.79
    ophon
    -0.79
    cius
    -0.78
    rown
    -0.77
    ĸļ
    -0.76
    haar
    -0.75
    kaya
    -0.74
    POSITIVE LOGITS
     Irma
    1.28
    ricane
    1.13
     Sandy
    1.09
     Katrina
    1.06
    ricanes
    0.96
     Hurricane
    0.91
     Harvey
    0.89
     Relief
    0.89
     relief
    0.88
     storms
    0.88
    Activations Density 0.026%

    No Known Activations