© 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. 16565
    Prev
    Next
    INDEX
    Explanations

    technical terms related to automation and efficiency in production processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to efficiency and resource characteristics

    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
    undrum
    -0.85
    keleton
    -0.83
    Woman
    -0.81
    selage
    -0.79
    asket
    -0.76
    ylum
    -0.76
    amus
    -0.75
    hirt
    -0.74
    iggurat
    -0.73
    irlfriend
    -0.73
    POSITIVE LOGITS
     ones
    1.84
     versions
    1.69
     instances
    1.43
     examples
    1.42
     counterparts
    1.41
     equivalents
    1.37
     implementations
    1.31
     replacements
    1.28
     cases
    1.28
     setups
    1.25
    Activations Density 0.463%

    No Known Activations