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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 13605
    Prev
    Next
    INDEX
    Explanations

    mentions of oceanic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to various oceans

    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
    TI
    -0.81
    TOP
    -0.75
    oulder
    -0.74
    enez
    -0.73
    Reloaded
    -0.72
    ENCE
    -0.72
    enance
    -0.69
    UGC
    -0.68
    éĹ
    -0.67
    Interstitial
    -0.67
    POSITIVE LOGITS
     Ocean
    1.15
    ographer
    1.07
    front
    0.95
     Atlantic
    0.91
    ographers
    0.89
    odon
    0.89
     Fisheries
    0.88
    ographic
    0.88
     basin
    0.84
     Spray
    0.83
    Activations Density 0.014%

    No Known Activations