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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10199
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of comparison or contrast using the word "some"

    oai_token-act-pair · gpt-3.5-turbo

    the term "some" in various contexts, indicating uncertainty or vagueness

    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
     yours
    -0.67
     Cycling
    -0.65
    +,
    -0.65
    gon
    -0.62
    uckle
    -0.61
    ributes
    -0.61
    acco
    -0.61
    ourses
    -0.59
     confronts
    -0.59
    gettable
    -0.57
    POSITIVE LOGITS
    place
    1.47
    ones
    1.36
     sort
    1.32
    body
    1.25
     kind
    1.16
     semblance
    1.08
    how
    1.08
     unspecified
    1.00
    ONE
    0.94
     combination
    0.91
    Activations Density 0.080%

    No Known Activations