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

    Neuronpedia

    Jacobian LensNEW
    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. 17764
    Prev
    Next
    INDEX
    Explanations

    references to the term "Cloud" that are not related to meteorology or weather

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Cloud" in various contexts

    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
    WAYS
    -0.88
    nings
    -0.76
     oxy
    -0.76
    enez
    -0.75
    merce
    -0.75
    Äĩ
    -0.73
     relativity
    -0.71
    pled
    -0.70
    iments
    -0.69
    uez
    -0.69
    POSITIVE LOGITS
     Imperium
    0.93
    Front
    0.81
     Skies
    0.78
    lake
    0.76
    haven
    0.76
    walker
    0.75
    burst
    0.74
    beard
    0.74
    leans
    0.74
     Cloud
    0.73
    Activations Density 0.035%

    No Known Activations