INDEX

Explanations

instances of the word "enter" and its variations in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 girasol

-0.53

 retval

-0.53

 NSMutable

-0.53

RefreshLayout

-0.51

сылкі

-0.51

attn

-0.50

Shot

-0.49

 Shot

-0.49

okohama

-0.48

 Verbrauch

-0.47

POSITIVE LOGITS

 entered

1.72

 enters

1.64

 Entering

1.59

 entering

1.58

Entering

1.54

entered

1.48

 enter

1.41

enters

1.39

 Entered

1.39

entering

1.37

Activations Density 0.169%

instances of the word "enter" and its variations in various contexts

No Comments

No Known Activations