© 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. 8-RES-JB
    11. 8602
    Prev
    Next
    INDEX
    Explanations

    references related to the presence of water in various celestial bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to water in various contexts, particularly in relation to planets and atmospheric conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.82
     adjourn
    -0.79
    ilet
    -0.75
    displayText
    -0.74
    utory
    -0.74
    Trust
    -0.73
    Privacy
    -0.73
    ettings
    -0.73
     Criminal
    -0.72
    Cert
    -0.72
    POSITIVE LOGITS
     molecules
    1.12
     ejected
    1.01
     particles
    1.00
     deposits
    1.00
     fragments
    0.96
     formation
    0.92
     Formation
    0.91
     masses
    0.89
     absorbs
    0.89
     molecule
    0.88
    Activations Density 0.257%

    No Known Activations