© 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. 7043
    Prev
    Next
    INDEX
    Explanations

    the word "shy."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shy."

    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
    女
    -0.93
    è¦ļéĨĴ
    -0.84
    ACTED
    -0.78
    urgy
    -0.73
    代
    -0.71
    RAW
    -0.71
    akeru
    -0.69
    ghazi
    -0.67
    quality
    -0.67
    ̶
    -0.67
    POSITIVE LOGITS
    ness
    1.06
    ety
    1.03
     shy
    0.90
    vana
    0.89
    uously
    0.82
    lish
    0.80
    eteenth
    0.76
    sters
    0.75
    nesses
    0.74
    rets
    0.74
    Activations Density 0.009%

    No Known Activations