© 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. 7-RES-JB
    11. 17873
    Prev
    Next
    INDEX
    Explanations

    names related to royalty

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "roy" and related terms, indicating a focus on a specific named entity or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INESS
    -0.77
    oter
    -0.75
    psons
    -0.73
    izoph
    -0.72
    agonist
    -0.72
    weights
    -0.68
    ocations
    -0.67
    RH
    -0.67
    oxide
    -0.65
    izers
    -0.65
    POSITIVE LOGITS
    ller
    0.69
    prints
    0.66
    doms
    0.66
    lett
    0.65
     Carney
    0.64
    aku
    0.64
    Marginal
    0.63
    ward
    0.63
     fide
    0.62
    sie
    0.61
    Activations Density 0.115%

    No Known Activations