© 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. 2-RES-JB
    11. 12458
    Prev
    Next
    INDEX
    Explanations

    names containing the word "Rosen"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Rosen" and its variants in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    į
    -0.89
    ¥
    -0.77
    orsi
    -0.75
    arily
    -0.74
    ³³³
    -0.72
    achusetts
    -0.69
    inct
    -0.66
    è¦ļéĨĴ
    -0.65
    ccording
    -0.64
    ģĸ
    -0.64
    POSITIVE LOGITS
    qv
    1.23
    wald
    1.16
    baum
    1.11
    quist
    1.10
     Rosen
    1.06
    lich
    1.06
    feld
    1.05
    lund
    1.00
    berg
    0.97
    stein
    0.93
    Activations Density 0.007%

    No Known Activations