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

    Neuronpedia

    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. 1895
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to differentiation and gradients

    oai_token-act-pair · gpt-3.5-turbo

    mathematical terms related to differential equations and gradients

    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
    stra
    -0.94
    bane
    -0.92
    fulness
    -0.83
    strap
    -0.82
    EF
    -0.79
    adows
    -0.79
    ogg
    -0.78
    ning
    -0.78
    ful
    -0.75
    hold
    -0.75
    POSITIVE LOGITS
     differential
    1.18
     equations
    0.99
     equation
    0.94
    iple
    0.91
    wcs
    0.89
     hemor
    0.87
     sclerosis
    0.85
     calculus
    0.85
     susceptibility
    0.83
    yip
    0.83
    Activations Density 0.012%

    No Known Activations