© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20099
    Prev
    Next
    INDEX
    Explanations

    numbers related to events or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to international summits and conferences

    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
    retch
    -0.78
    panic
    -0.64
     gren
    -0.63
    enegger
    -0.62
     warr
    -0.57
    agna
    -0.57
     sprint
    -0.57
    --------------------------------------------------------
    -0.56
     merit
    -0.56
     Hallow
    -0.55
    POSITIVE LOGITS
    xual
    0.94
    Cs
    0.81
    âĢ²
    0.77
    FY
    0.76
    Gs
    0.71
    sers
    0.68
    Ds
    0.67
     suprem
    0.67
    Lex
    0.67
    LR
    0.66
    Activations Density 0.100%

    No Known Activations