INDEX

Explanations

references to conclusions or remarks made after analysis or results

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

چه

-0.43

 appena

-0.43

Full

-0.43

OGND

-0.43

full

-0.42

times

-0.42

 asupra

-0.41

邏

-0.41

ঞ

-0.41

POSITIVE LOGITS

__":

0.85

 nakalista

0.83

onOptions

0.81

 الرياضيه

0.80

afficheront

0.78

 onAnimation

0.74

^(@)

0.72

ьаж

0.72

__':

0.71

djangoproject

0.70

Activations Density 0.274%

references to conclusions or remarks made after analysis or results

No Comments

No Known Activations