© 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. 0-RES-JB
    11. 5107
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named "Ge" and varying combinations of other characters

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ge" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weeney
    -0.72
    cooked
    -0.67
     asleep
    -0.65
    adden
    -0.64
     puppies
    -0.64
    amac
    -0.63
    arers
    -0.62
     needles
    -0.61
     NIGHT
    -0.61
     receptions
    -0.60
    POSITIVE LOGITS
     Ge
    3.74
    Ge
    2.45
     ge
    2.07
     Geo
    1.59
    ge
    1.47
     Geological
    1.39
     geo
    1.26
     Zo
    1.24
     GE
    1.23
     geop
    1.22
    Activations Density 0.009%

    No Known Activations