© 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 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. 9-RES-JB
    11. 19648
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "The"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "the" and related determiners in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colored
    -1.09
     someday
    -0.96
    anooga
    -0.95
    é¾įåĸļ士
    -0.94
    caliber
    -0.93
     toward
    -0.93
    centered
    -0.92
    bors
    -0.92
    zona
    -0.91
     gotten
    -0.91
    POSITIVE LOGITS
     organisation
    1.65
     programme
    1.57
     organisers
    1.50
     £
    1.45
     centre
    1.44
     UK
    1.41
     Scottish
    1.36
     NHS
    1.36
     ageing
    1.35
     BBC
    1.33
    Activations Density 0.680%

    No Known Activations