INDEX

Explanations

numerical data or quantities mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

//

-0.82

 EconPapers

-0.74

googleapis

-0.65

-0.57

pidou

-0.54

cassert

-0.53

Jereo

-0.53

foe

-0.52

 ostavi

-0.51

 שוליים

-0.51

POSITIVE LOGITS

 dozen

0.92

<bos>

0.92

 dozens

0.81

dozen

0.81

 numerous

0.66

several

0.62

 hundreds

0.61

numbered

0.61

 ſeveral

0.61

InjectMocks

0.61

Activations Density 0.487%

numerical data or quantities mentioned in the text

No Comments

No Known Activations