© 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. 6-RES-JB
    11. 16910
    Prev
    Next
    INDEX
    Explanations

    the name "Abu" combined with various other names or words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Abu" associated with various figures or leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.83
    NetMessage
    -0.79
    xual
    -0.77
    eries
    -0.73
     Dorothy
    -0.67
    intendent
    -0.67
     PBS
    -0.67
     Titanic
    -0.66
     Pixie
    -0.66
    Ö¼
    -0.66
    POSITIVE LOGITS
     Dhabi
    1.34
     Bakr
    1.16
    hammad
    0.91
    rahim
    0.89
    ghan
    0.87
    aida
    0.85
    dullah
    0.85
     Ali
    0.85
    querque
    0.83
    ji
    0.82
    Activations Density 0.019%

    No Known Activations