INDEX

Explanations

greetings and salutations in various languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bave

-0.63

[+

-0.62

 sumpay

-0.62

 ContentValues

-0.60

>');

-0.60

ssymb

-0.60

 собі

-0.59

jstor

-0.58

fortawesome

-0.58

 kaynağından

-0.58

POSITIVE LOGITS

 hello

1.11

 Hello

1.10

Hello

1.10

hello

0.94

Greetings

0.92

HELLO

0.90

Greeting

0.89

 HELLO

0.89

Привет

0.87

 Greetings

0.86

Activations Density 0.101%

greetings and salutations in various languages

No Comments

No Known Activations