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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12401
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles that indicate relationships or connections between elements in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a couple of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.83
    ario
    -0.76
    vale
    -0.72
    ynthesis
    -0.71
    opus
    -0.71
    VS
    -0.70
    cape
    -0.70
    dn
    -0.70
    ĸļ
    -0.69
    netflix
    -0.68
    POSITIVE LOGITS
     occasions
    1.00
     hundred
    0.99
     dozen
    0.95
     factors
    0.91
     them
    0.90
     times
    0.90
     different
    0.90
     paragraphs
    0.89
     weeks
    0.87
     interesting
    0.84
    Activations Density 0.079%

    No Known Activations