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. 0-RES-JB
    6. 22152
    Prev
    Next
    INDEX
    Explanations

    references to the sea, such as sea levels, sea life, sea otters, and sea ice

    oai_token-act-pair · gpt-3.5-turbo

    references to the sea and related environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pun
    -0.76
    handler
    -0.71
    script
    -0.70
    zy
    -0.69
    ner
    -0.68
     Parenthood
    -0.66
    NER
    -0.65
    Assistant
    -0.65
    respons
    -0.64
    operated
    -0.64
    POSITIVE LOGITS
     sea
    3.74
    Sea
    2.49
     Sea
    2.47
     seas
    2.38
     ocean
    2.19
    sea
    2.12
     oceans
    1.87
     Seas
    1.80
     seaw
    1.76
     seaf
    1.75
    Activations Density 0.018%

    No Known Activations