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. 3-RES-JB
    6. 19664
    Prev
    Next
    INDEX
    Explanations

    references to rising sea levels

    oai_token-act-pair · gpt-3.5-turbo

    references to sea level and its changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBLE
    -0.90
    arantine
    -0.87
    etts
    -0.83
    Interstitial
    -0.83
    iom
    -0.82
    undle
    -0.82
    sbm
    -0.81
    Filename
    -0.79
    âĶģ
    -0.77
    STEP
    -0.76
    POSITIVE LOGITS
    plane
    0.94
     sea
    0.92
     crocod
    0.92
     monster
    0.90
     lions
    0.88
     Sea
    0.85
     serpent
    0.83
     ocean
    0.81
     shore
    0.81
     Kraken
    0.80
    Activations Density 0.009%

    No Known Activations