© 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. 2-RES-JB
    11. 3858
    Prev
    Next
    INDEX
    Explanations

    references to the term "Net"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Net" in various contexts, likely related to networking or internet topics

    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
    Downloadha
    -0.71
    =-=-=-=-
    -0.71
     annexed
    -0.70
    士
    -0.68
     choir
    -0.66
    «ĺ
    -0.66
    axter
    -0.64
     Templar
    -0.64
    âĵĺ
    -0.63
    interstitial
    -0.63
    POSITIVE LOGITS
    anyahu
    1.23
    izen
    1.22
    izens
    1.21
    rek
    0.98
    tle
    0.97
    aji
    0.94
    Net
    0.86
    rw
    0.84
    roots
    0.84
    heastern
    0.83
    Activations Density 0.004%

    No Known Activations