© 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. 2-RES-JB
    11. 22203
    Prev
    Next
    INDEX
    Explanations

    names and references related to someone named "Sar"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sar" in various contexts

    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
    iculty
    -0.74
    mercial
    -0.73
    Reviewer
    -0.72
    STER
    -0.65
    verified
    -0.64
    éĹĺ
    -0.63
     Billboard
    -0.62
     curfew
    -0.62
     Dangerous
    -0.61
    cellent
    -0.61
    POSITIVE LOGITS
     Sar
    1.12
    kees
    1.07
    thal
    1.00
    ashtra
    0.97
    ban
    0.96
    athe
    0.91
    ona
    0.90
    anus
    0.89
    abeth
    0.89
    andon
    0.88
    Activations Density 0.005%

    No Known Activations