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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 25
    Prev
    Next
    INDEX
    Explanations

    key terms related to glaciers and Greenland

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Greenland and associated natural features or wildlife

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ento
    -0.94
    colo
    -0.91
    oslav
    -0.85
    uana
    -0.85
    NES
    -0.82
    hester
    -0.81
    omp
    -0.79
    hea
    -0.78
    ategory
    -0.78
    atari
    -0.77
    POSITIVE LOGITS
    ipeg
    0.81
     glaciers
    0.76
     glacier
    0.74
     whales
    0.73
     rink
    0.71
     Dunham
    0.71
     slope
    0.69
    berries
    0.68
    ufact
    0.68
     deer
    0.67
    Activations Density 0.042%

    No Known Activations