INDEX

Explanations

phrases that indicate necessity or essential conditions

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

dymyr

-0.87

oliber

-0.85

ValueStyle

-0.79

RunWith

-0.71

 cucchiaio

-0.70

Chin

-0.69

colhead

-0.67

चाल

-0.67

 Poul

-0.67

 Blazers

-0.67

POSITIVE LOGITS

Necessary

1.43

 necessary

1.31

 needed

1.29

 Necessary

1.23

necessary

1.16

 necessity

1.15

必要

1.15

 necessities

1.15

needed

1.12

 required

1.10

Activations Density 0.088%

phrases that indicate necessity or essential conditions

No Comments

No Known Activations