© 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. 1-RES-JB
    11. 3831
    Prev
    Next
    INDEX
    Explanations

    proper nouns mentioning the name "Des"

    oai_token-act-pair · gpt-3.5-turbo

    the proper noun "Des," likely indicating a focus on locations or entities named Des

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
     internationally
    -0.71
    glers
    -0.67
    atown
    -0.66
    hetti
    -0.65
    osate
    -0.62
     CLR
    -0.62
     Penguin
    -0.62
    iterranean
    -0.60
     Klaus
    -0.60
    POSITIVE LOGITS
     Moines
    1.15
    perate
    1.11
    ync
    1.07
    cend
    1.03
    criptions
    0.92
    erve
    0.90
    eret
    0.87
    erves
    0.85
    semb
    0.84
    pell
    0.82
    Activations Density 0.004%

    No Known Activations