© 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. 2-RES-JB
    11. 15458
    Prev
    Next
    INDEX
    Explanations

    instances where the abbreviation "eg" is used

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "eg," which likely indicates examples or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.72
    DERR
    -0.70
     doub
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    Marsh
    -0.62
     Hots
    -0.59
    thia
    -0.59
     Heard
    -0.58
     Fas
    -0.57
     Printed
    -0.56
    POSITIVE LOGITS
    ardless
    1.03
    asus
    1.01
    raphics
    0.97
    entric
    0.92
    roup
    0.90
    adr
    0.86
    rees
    0.85
    uild
    0.83
    aming
    0.83
    ift
    0.82
    Activations Density 0.007%

    No Known Activations