INDEX

Explanations

Japanese characters and phrases that suggest waiting or anticipation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

in

-0.69

-0.59

-0.58

-0.56

one

-0.53

-0.51

 most

-0.51

new

-0.51

-0.50

POSITIVE LOGITS

UnusedPrivate

1.17

 للاسماء

1.13

bootstrapcdn

1.09

 Reſ

1.06

Efq

1.06

+#+#

1.06

DeleteBehavior

1.04

Personensuche

1.03

InputBorder

0.99

 وتسجيلات

0.97

Activations Density 0.242%

Japanese characters and phrases that suggest waiting or anticipation

No Comments

No Known Activations