INDEX

Explanations

instances of the word "point" and its variations, indicating an emphasis on highlighting or indicating information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ⓘ

-0.65

mybatisplus

-0.62

bootstrapcdn

-0.51

fortawesome

-0.51

évaluateur

-0.51

$_['

-0.49

IActionResult

-0.48

 bäst

-0.46

gpl

-0.46

UIControlState

-0.45

POSITIVE LOGITS

 pointed

0.92

 pointing

0.85

 fingers

0.81

 finger

0.80

 attention

0.78

finger

0.77

fingers

0.72

Fingers

0.68

 указыва

0.68

 doigt

0.67

Activations Density 0.089%

instances of the word "point" and its variations, indicating an emphasis on highlighting or indicating information

No Comments

No Known Activations