© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 661
    Prev
    Next
    INDEX
    Explanations

    keywords related to website visits and internet traffic

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vis."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.72
    anyahu
    -0.69
    ropy
    -0.67
    RAW
    -0.65
     CLR
    -0.64
     Carnegie
    -0.62
    ¶ħ
    -0.62
    Ĥª
    -0.61
    AUT
    -0.61
    ļé
    -0.61
    POSITIVE LOGITS
    ibility
    1.22
    ibly
    1.08
    itors
    1.05
    ited
    0.97
    itor
    0.96
     versa
    0.91
    ibl
    0.88
    ports
    0.85
    idon
    0.85
    portation
    0.85
    Activations Density 0.027%

    No Known Activations