INDEX

Explanations

instances of the word "first" and its variations, indicating a focus on initial occurrences or rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 désol

-0.47

kurang

-0.46

úrese

-0.44

 posisi

-0.43

 stør

-0.42

↵↵

-0.41

↵↵↵↵

-0.40

adilan

-0.39

ाम

-0.39

 кӀ

-0.38

POSITIVE LOGITS

SharedDtor

0.80

клопе

0.79

PropertyChanging

0.76

UnusedPrivate

0.75

SourceChecksum

0.75

bootstrapcdn

0.74

HasAnnotation

0.73

 *)__

0.73

Попис

0.71

culable

0.71

Activations Density 0.279%

instances of the word "first" and its variations, indicating a focus on initial occurrences or rankings

No Comments

No Known Activations