Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 470
    Prev
    Next
    INDEX
    Explanations

    names containing the letter sequence "Kr"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the surname "Kr" in various contexts

    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
     Dragonbound
    -0.87
     quo
    -0.73
    ORGE
    -0.70
     Samoa
    -0.69
    å§«
    -0.68
    journal
    -0.66
    ãģ¦
    -0.66
    eering
    -0.65
     tune
    -0.63
    âĸ¬âĸ¬
    -0.62
    POSITIVE LOGITS
    assic
    1.23
    usk
    1.18
    ©¶æ¥µ
    1.07
    istani
    1.03
    anny
    1.00
    asus
    0.97
    uder
    0.96
    acy
    0.96
    utch
    0.95
    icer
    0.95
    Activations Density 0.006%

    No Known Activations