© 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. 5019
    Prev
    Next
    INDEX
    Explanations

    words containing 'che'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "che" 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
     fiscal
    -0.61
     Redmond
    -0.61
     powers
    -0.60
     prism
    -0.60
     Lutheran
    -0.60
     procedural
    -0.59
     parent
    -0.58
     Indonesia
    -0.58
     Void
    -0.58
     replication
    -0.58
    POSITIVE LOGITS
    che
    4.47
    chel
    2.22
    chet
    2.03
    Che
    1.97
    ches
    1.96
    cher
    1.91
    chery
    1.82
    ched
    1.73
    chen
    1.72
    chers
    1.65
    Activations Density 0.008%

    No Known Activations