© 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. 22166
    Prev
    Next
    INDEX
    Explanations

    words related to the country of Malaysia

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Malaysia."

    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
    ality
    -0.71
    ISON
    -0.68
    ש
    -0.65
     clen
    -0.63
    Reviewer
    -0.63
     Sop
    -0.61
    ographic
    -0.60
    PB
    -0.59
    NRS
    -0.59
     po
    -0.59
    POSITIVE LOGITS
    cale
    1.17
    ystem
    1.00
    ayers
    0.99
    ource
    0.98
    haw
    0.90
    hirt
    0.89
    chool
    0.86
    rand
    0.86
    outh
    0.85
    creen
    0.84
    Activations Density 0.009%

    No Known Activations