© 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. 4-RES-JB
    11. 7198
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the concept of "Ron" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ron" within various contexts

    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
     SOS
    -0.73
     Saras
    -0.72
    tub
    -0.72
     Sap
    -0.70
    TPS
    -0.69
     Norn
    -0.67
     Cyp
    -0.65
    UGE
    -0.63
     Gim
    -0.63
     LIA
    -0.63
    POSITIVE LOGITS
    auts
    1.04
     Collider
    0.97
    aldo
    0.94
    stadt
    0.92
    igans
    0.92
    omical
    0.91
    ising
    0.86
    ially
    0.85
    ework
    0.81
    autical
    0.80
    Activations Density 0.014%

    No Known Activations