INDEX

Explanations

references to research studies and their results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Chwiliwch

-0.82

>{@

-0.80

ContentAsync

-0.74

 Biôgrafia

-0.73

GEBURTSDATUM

-0.71

 cref

-0.70

клопе

-0.70

 насељу

-0.70

']))

-0.68

jstor

-0.66

POSITIVE LOGITS

0.57

⇓

0.47

•

0.44

–

0.41

 unintentionally

0.40

bit

0.40

lieving

0.39

 gắng

0.38

 interestingly

0.38

••

0.37

Activations Density 0.604%

references to research studies and their results

No Comments

No Known Activations