© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "try"

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the word "try" 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
    edly
    -0.66
     Goth
    -0.63
    Tal
    -0.62
    dylib
    -0.61
    head
    -0.60
    models
    -0.59
    appropriately
    -0.59
    ZA
    -0.59
    liber
    -0.59
    conscious
    -0.58
    POSITIVE LOGITS
    nir
    0.80
     try
    0.76
     unsuccessfully
    0.75
     tried
    0.73
    onies
    0.72
    Try
    0.67
    ters
    0.66
    ichick
    0.65
    ":"/
    0.65
    âķIJâķIJ
    0.65
    Activations Density 0.031%

    No Known Activations