© 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. 6178
    Prev
    Next
    INDEX
    Explanations

    words related to the name "ko"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "ko" which could indicate a focus on specific names or terms

    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
    Þ
    -0.75
     behavi
    -0.74
    Subject
    -0.73
     thous
    -0.72
    IDENT
    -0.71
    Ü
    -0.71
    icist
    -0.69
     narrator
    -0.68
    Interstitial
    -0.67
    Correct
    -0.66
    POSITIVE LOGITS
    zzi
    1.16
    ko
    1.07
    ppa
    1.06
    ichi
    0.99
    pps
    0.98
    opa
    0.98
    zy
    0.95
    zzo
    0.93
    ota
    0.93
    ek
    0.92
    Activations Density 0.007%

    No Known Activations