INDEX

Explanations

terms and phrases that indicate importance and significance in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

MemoryWarning

-0.44

OptionsMenu

-0.37

 unprepared

-0.32

enumii

-0.31

UserScript

-0.29

PreAuthorize

-0.29

詰

-0.29

getWriter

-0.28

 useStyles

-0.28

 McFarland

-0.28

POSITIVE LOGITS

LookAnd

0.60

 ویکی‌پدی

0.59

 protoimpl

0.57

 Мексичка

0.57

Tikang

0.55

 parachoque

0.55

новништво

0.55

 dévelo

0.55

 CreateTagHelper

0.55

 ſind

0.54

Activations Density 0.025%

terms and phrases that indicate importance and significance in the text

No Comments

No Known Activations