© 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. 17519
    Prev
    Next
    INDEX
    Explanations

    references to new or recent events or changes

    oai_token-act-pair · gpt-3.5-turbo

    the term "new" 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
    76561
    -0.80
    umenthal
    -0.78
    Zip
    -0.75
    cius
    -0.75
     Originally
    -0.75
    ertodd
    -0.75
    ecause
    -0.73
    xual
    -0.73
    agree
    -0.72
    ;;;;
    -0.71
    POSITIVE LOGITS
    bies
    1.38
    bie
    1.37
     arrivals
    1.24
     millennium
    1.16
     incarnation
    0.97
     hires
    0.97
     edition
    0.96
     entrants
    0.95
     generation
    0.95
     additions
    0.95
    Activations Density 0.089%

    No Known Activations