© 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. 5930
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Daniel" or similar variants

    oai_token-act-pair · gpt-3.5-turbo

    words related to an individual's last name

    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
    ricular
    -0.80
    hedral
    -0.74
     odds
    -0.65
    ramid
    -0.63
    hered
    -0.62
     fav
    -0.61
     Printed
    -0.61
     untold
    -0.60
    ulhu
    -0.59
    ctica
    -0.59
    POSITIVE LOGITS
    ibrary
    1.06
    iel
    0.95
    abel
    0.91
    anguage
    0.89
    ands
    0.88
    naire
    0.86
    er
    0.86
    stadt
    0.83
    inski
    0.82
    ounge
    0.81
    Activations Density 0.012%

    No Known Activations