INDEX

Explanations

phrases indicating an effect or impact on subjects or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.61

-0.60

 القيام

-0.59

айт

-0.58

algo

-0.56

έ

-0.56

-0.55

si

-0.55

-0.54

POSITIVE LOGITS

 affecting

1.37

 AFFECT

1.33

 affects

1.31

 Affecting

1.31

 Affects

1.30

 influencing

1.27

 Affected

1.26

 affect

1.25

 AssemblyTitle

1.22

affect

1.22

Activations Density 0.228%

phrases indicating an effect or impact on subjects or situations

No Comments

No Known Activations