© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15337
    Prev
    Next
    INDEX
    Explanations

    mentions of ice sheets, primarily Greenland and Antarctic ice sheets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ice sheets and their properties

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

    No Comments

    Negative Logits
    rompt
    -0.84
    INGTON
    -0.82
    ilitary
    -0.79
    isites
    -0.75
    adesh
    -0.75
    edy
    -0.73
    merce
    -0.72
    ENTION
    -0.72
    itsch
    -0.72
    aughs
    -0.71
    POSITIVE LOGITS
    breaker
    1.03
     rink
    0.99
    breakers
    0.98
     cream
    0.92
    caps
    0.88
     skating
    0.87
    flake
    0.86
     lake
    0.85
     caves
    0.84
     crystals
    0.82
    Activations Density 0.009%

    No Known Activations