INDEX

Explanations

repetitions of the word "same"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.70

 DiCaprio

-0.68

 האם

-0.66

hört

-0.65

setupUi

-0.59

{}/

-0.59

TRIBUN

-0.58

льше

-0.58

pios

-0.57

Jegyzetek

-0.56

POSITIVE LOGITS

 same

2.31

Same

2.29

SAME

2.26

same

2.23

 Same

2.15

 SAME

2.12

 samme

1.69

 samma

1.67

 mesma

1.55

 hetzelfde

1.50

Activations Density 0.127%

repetitions of the word "same"

No Comments

No Known Activations