INDEX

Explanations

references to durations and time intervals in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 متعلقه

-0.74

 للمعارف

-0.73

 يتيمه

-0.69

-0.65

SharedDtor

-0.64

ArgsConstructor

-0.64

 useRouter

-0.64

+#+#

-0.64

 utafitiHapana

-0.63

PreferredItem

-0.61

POSITIVE LOGITS

 prolonged

0.91

longed

0.77

 longer

0.71

 duration

0.69

 extended

0.66

 Brief

0.63

 sustained

0.62

 Extended

0.62

持久

0.61

longer

0.61

Activations Density 0.498%

references to durations and time intervals in various contexts

No Comments

No Known Activations