© 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. 10-RES-JB
    11. 3260
    Prev
    Next
    INDEX
    Explanations

    references to completeness or entirety

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "entire" as it relates to comprehensive situations or subjects

    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
    chairs
    -0.88
    bits
    -0.83
    friends
    -0.79
    none
    -0.75
    facts
    -0.75
    pots
    -0.73
    =-=-=-=-=-=-=-=-
    -0.72
    bis
    -0.69
    plugins
    -0.69
    Examples
    -0.69
    POSITIVE LOGITS
     spectrum
    1.05
     arsenal
    1.00
     continent
    1.00
     length
    0.94
     lifespan
    0.93
     globe
    0.92
     swath
    0.92
     duration
    0.91
     range
    0.90
     repertoire
    0.89
    Activations Density 0.039%

    No Known Activations