INDEX

Explanations

the letter 'f' and characters associated with it, likely indicating a focus on words or terms starting with or heavily featuring 'f' in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 manuelle

-0.38

Totale

-0.37

awsze

-0.37

⋱

-0.36

 bedien

-0.36

 zám

-0.36

 avviene

-0.36

Демо

-0.35

 étrangère

-0.35

 Khusus

-0.35

POSITIVE LOGITS

<bos>

0.69

تقاوى

0.60

 ویکی‌پدی

0.56

 ProtoMessage

0.54

writeFieldEnd

0.54

{?}

0.53

}{@

0.53

ChildScrollView

0.52

MigrationBuilder

0.52

 CreateTagHelper

0.49

Activations Density 0.240%

the letter 'f' and characters associated with it, likely indicating a focus on words or terms starting with or heavily featuring 'f' in various contexts

No Known Activations