© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2848
    Prev
    Next
    INDEX
    Explanations

    words related to programming functions or functional programming

    oai_token-act-pair · gpt-3.5-turbo

    references to programming functions and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cott
    -0.85
    chell
    -0.70
    olson
    -0.70
    creen
    -0.70
    vae
    -0.69
     Lank
    -0.69
    chant
    -0.67
    corn
    -0.67
    bows
    -0.66
     Reporter
    -0.65
    POSITIVE LOGITS
    ality
    1.26
    alities
    0.98
    ional
    0.90
    ivity
    0.89
    ative
    0.86
    aries
    0.80
    icular
    0.80
    inic
    0.79
    ational
    0.78
    arity
    0.77
    Activations Density 0.028%

    No Known Activations