INDEX

Explanations

terms related to injuries or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للمعارف

-0.57

الحياه

-0.56

ⓧ

-0.51

دانشنامهٔ

-0.49

__["

-0.49

rawDesc

-0.47

 Zayed

-0.45

 còn

-0.44

CTR

-0.44

sob

-0.44

POSITIVE LOGITS

 inning

0.86

 bottom

0.82

 innings

0.71

bottom

0.70

 BOTTOM

0.68

Bottom

0.66

__;

0.65

 Bottom

0.60

 seventh

0.59

top

0.58

Activations Density 0.078%

terms related to injuries or medical conditions

No Comments

No Known Activations