© 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. 10-RES-JB
    11. 16558
    Prev
    Next
    INDEX
    Explanations

    words related to industrial settings and tools

    oai_token-act-pair · gpt-3.5-turbo

    references to industrial-grade products and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ell
    -0.71
     accuser
    -0.69
     Burr
    -0.68
     Meadows
    -0.68
     Norris
    -0.66
     Bagg
    -0.66
     Weld
    -0.66
     redes
    -0.65
     sockets
    -0.64
     Maher
    -0.64
    POSITIVE LOGITS
    style
    1.72
    grade
    1.65
    themed
    1.56
    inspired
    1.52
    minded
    1.49
    ready
    1.47
    oriented
    1.45
    friendly
    1.45
    level
    1.40
    type
    1.39
    Activations Density 0.073%

    No Known Activations