© 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. 4-RES-JB
    11. 19928
    Prev
    Next
    INDEX
    Explanations

    email addresses related to a specific person named Njad Vance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual

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

    No Comments

    Negative Logits
     Surviv
    -0.99
     Dying
    -0.80
     Myst
    -0.72
    cule
    -0.71
     cryst
    -0.68
     Romanian
    -0.68
    MENT
    -0.67
     reluct
    -0.67
     proport
    -0.65
    é¾
    -0.65
    POSITIVE LOGITS
    vance
    1.26
    pour
    1.00
    jad
    0.97
    hu
    0.86
    enh
    0.80
    livion
    0.79
    emet
    0.78
    eering
    0.76
    mun
    0.76
    enstein
    0.76
    Activations Density 0.013%

    No Known Activations