© 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. 20900
    Prev
    Next
    INDEX
    Explanations

    syntax-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to programming syntax

    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
     Kore
    -0.84
    male
    -0.75
    conom
    -0.74
    zona
    -0.73
     Gund
    -0.71
     Gunn
    -0.70
    agher
    -0.70
    olphin
    -0.69
    IVERS
    -0.68
    evil
    -0.68
    POSITIVE LOGITS
     syntax
    1.18
    ntax
    0.98
     notation
    0.91
     highlighting
    0.87
     substitution
    0.85
    hess
    0.83
     parsing
    0.82
     definitions
    0.82
     parser
    0.81
     shorthand
    0.81
    Activations Density 0.021%

    No Known Activations