INDEX

Explanations

questions about opinions and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

viti

-0.56

 }}"></

-0.51

Trained

-0.47

perk

-0.43

hn

-0.39

 Post

-0.39

 USES

-0.39

 "'";

-0.39

»

-0.39

 świ

-0.39

POSITIVE LOGITS

RegistryLite

0.98

 Baillargeon

0.87

 ErrIntOverflow

0.76

ResponseWriter

0.75

 оригіналу

0.73

 consultato

0.70

ostante

0.70

tagHelperRunner

0.70

 sánh

0.68

contentLoaded

0.68

Activations Density 0.073%

questions about opinions and preferences

No Comments

No Known Activations