INDEX

Explanations

phrases that indicate relative comparisons or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 chanti

-0.72

 Außerdem

-0.61

 Pizz

-0.60

 pizz

-0.59

imento

-0.58

 Mendez

-0.58

ambiguation

-0.58

样的

-0.58

 Habana

-0.57

שי

-0.57

POSITIVE LOGITS

 RELATIVE

1.22

 relative

1.21

 Relative

1.15

Relative

1.10

relative

1.08

RELATIVE

1.06

RelativeLayout

1.02

 ElementRef

0.97

 relati

0.95

ViewFeatures

0.95

Activations Density 0.161%

phrases that indicate relative comparisons or measurements

No Comments

No Known Activations