© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 9058
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Korver" or "Koran"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or terms related to "Kor" and "Koran."

    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
    enegger
    -0.88
    20439
    -0.86
    ãģ¦
    -0.82
     Sussex
    -0.71
     Democr
    -0.71
    æĢ
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
    ATURES
    -0.67
    ATURE
    -0.67
    ships
    -0.67
    POSITIVE LOGITS
    anic
    1.11
     Klux
    1.09
     Kor
    1.07
    atown
    0.90
    kat
    0.90
    adian
    0.89
    onite
    0.88
     Lumpur
    0.86
    imura
    0.85
    enei
    0.85
    Activations Density 0.014%

    No Known Activations