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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18349
    Prev
    Next
    INDEX
    Explanations

    phrases related to the melting of ice in polar regions, particularly the Arctic and Antarctic ice sheets

    oai_token-act-pair · gpt-3.5-turbo

    references to sea ice and its implications in the Arctic and Antarctic regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rompt
    -0.85
    sembly
    -0.80
    INGTON
    -0.78
    aughs
    -0.77
    isites
    -0.75
    itsch
    -0.73
    ilitary
    -0.73
    =-=-=-=-=-=-=-=-
    -0.72
    ENTION
    -0.72
    ivating
    -0.72
    POSITIVE LOGITS
    breaker
    0.93
     drift
    0.87
    breakers
    0.84
     caps
    0.83
     buildup
    0.82
     rink
    0.82
     caves
    0.82
     lake
    0.81
    flake
    0.81
     shelves
    0.81
    Activations Density 0.012%

    No Known Activations