INDEX

Explanations

occurrences of the word "save" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

новништво

-0.73

::-

-0.65

rizona

-0.63

 rêver

-0.62

 craindre

-0.61

diensten

-0.59

ucson

-0.58

 pensent

-0.58

évaluateur

-0.58

StyleSheet

-0.57

POSITIVE LOGITS

save

1.71

 Save

1.56

 save

1.55

Save

1.54

 SAVE

1.41

SAVE

1.24

 saves

1.03

 saved

0.95

 Saves

0.95

Sav

0.95

Activations Density 0.040%

occurrences of the word "save" and its variations

No Comments

No Known Activations