INDEX

Explanations

instances of the word "to" used 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utafitiHapana

-0.69

 StatefulWidget

-0.66

躇

-0.65

WebVitals

-0.64

 useDispatch

-0.54

 saites

-0.54

 لكرة

-0.52

rimir

-0.51

ISupport

-0.51

 CreateTagHelper

-0.51

POSITIVE LOGITS

ècie

0.74

 مرئيه

0.69

TagMode

0.61

IsMutable

0.61

 respectively

0.59

adpleegd

0.58

الحياه

0.57

 volna

0.57

HasBeenSet

0.56

 respectivement

0.56

Activations Density 0.360%

instances of the word "to" used in various contexts

No Comments

No Known Activations