© 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. 0-RES-JB
    11. 6216
    Prev
    Next
    INDEX
    Explanations

    situations or contexts where an action or rule should be applied

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "apply" and its variations in different 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
     Independence
    -0.64
     Rus
    -0.61
     Ruins
    -0.61
     Ple
    -0.61
    Leaks
    -0.58
     Tonight
    -0.58
     Sle
    -0.58
     Atmosp
    -0.58
     Sind
    -0.58
     fal
    -0.57
    POSITIVE LOGITS
     apply
    3.62
     Apply
    2.79
    apply
    2.65
    Apply
    2.52
     applies
    2.39
     applied
    2.11
     applying
    2.03
     Applic
    1.49
     applic
    1.45
    Applic
    1.45
    Activations Density 0.019%

    No Known Activations