© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or physical environments, particularly near bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ide"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     custody
    -0.61
     cand
    -0.58
     resumed
    -0.57
     bron
    -0.55
     charred
    -0.55
    HOU
    -0.55
     Bows
    -0.55
     restraints
    -0.55
     BAL
    -0.54
     Newfoundland
    -0.54
    POSITIVE LOGITS
    ide
    4.63
    ides
    3.04
    IDE
    2.72
    ided
    2.14
    IDES
    2.14
    iding
    2.12
    ider
    1.83
    iders
    1.72
    idal
    1.64
    idation
    1.39
    Activations Density 0.010%

    No Known Activations