© 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. 6040
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to specific names or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to the acronym "KE" and related variations

    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
    naire
    -0.74
    ional
    -0.73
    inally
    -0.71
    actionDate
    -0.69
    inant
    -0.69
    inatory
    -0.67
    inators
    -0.67
    acious
    -0.65
    acity
    -0.64
    roman
    -0.62
    POSITIVE LOGITS
    KE
    1.19
    YS
    1.09
    VO
    1.08
    LEY
    1.03
    IRO
    1.01
    LAND
    0.90
    VID
    0.88
    VERS
    0.86
    VICE
    0.86
    ITH
    0.85
    Activations Density 0.004%

    No Known Activations