© 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. 3-RES-JB
    6. 9757
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Rowan" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Rowland" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.89
    £ı
    -0.77
     medi
    -0.75
     mediation
    -0.75
    ãĥ¤
    -0.73
     dilig
    -0.73
     competence
    -0.70
    bernatorial
    -0.69
    urai
    -0.69
     regulate
    -0.69
    POSITIVE LOGITS
    dies
    1.36
    dy
    1.28
    Row
    1.03
    hani
    1.01
    row
    0.96
    Topic
    0.96
    leys
    0.96
     Row
    0.95
    ley
    0.94
    away
    0.93
    Activations Density 0.007%

    No Known Activations