INDEX

Explanations

instances of comparison and comparison-related terms

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

Not in Any Lists

No Comments

Negative Logits

菁

-0.42

saraba

-0.42

まま

-0.40

fluid

-0.40

Slee

-0.39

Offic

-0.38

 münd

-0.38

 TAMBIÉN

-0.38

fonds

-0.37

 عنوان

-0.37

POSITIVE LOGITS

 compare

3.42

 comparison

3.39

 comparing

3.28

 compares

3.20

 comparisons

3.16

 Compare

3.02

compare

3.00

 Comparison

2.91

Compare

2.91

comparison

2.89

Activations Density 0.141%

instances of comparison and comparison-related terms

No Comments

No Known Activations