© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18029
    Prev
    Next
    INDEX
    Explanations

    the word "join" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "join" and its variations, as well as related terms

    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
     Seah
    -0.75
     Yuan
    -0.70
     Richards
    -0.68
     Dah
    -0.66
     crude
    -0.64
     shells
    -0.62
     Rud
    -0.62
     kits
    -0.62
     Gad
    -0.62
     scaven
    -0.62
    POSITIVE LOGITS
    join
    4.51
    joined
    2.50
    joining
    2.46
    Join
    1.21
    united
    1.13
    hello
    1.07
    company
    1.04
    Premium
    1.03
    escape
    1.03
     Join
    1.00
    Activations Density 0.035%

    No Known Activations