© 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. 10-RES-JB
    11. 14105
    Prev
    Next
    INDEX
    Explanations

    the word "most" followed by some description

    oai_token-act-pair · gpt-3.5-turbo

    superlative expressions indicating the highest degree of something, particularly "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    instead
    -0.82
    roo
    -0.77
    é¾įåĸļ士
    -0.77
    culosis
    -0.75
    ysc
    -0.75
    heid
    -0.75
    æ©
    -0.73
    halla
    -0.73
    uci
    -0.72
    runs
    -0.72
    POSITIVE LOGITS
     obvious
    1.47
     notable
    1.42
     noticeable
    1.38
     important
    1.38
     interesting
    1.33
     salient
    1.32
     intriguing
    1.31
     glaring
    1.29
     worrisome
    1.27
     noteworthy
    1.26
    Activations Density 0.048%

    No Known Activations