INDEX

Explanations

phrases that involve the concept of inclusion or factors from a list

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 houſe

-0.91

 purpoſe

-0.88

 ſtate

-0.77

 ſche

-0.77

 cauſe

-0.76

 ſhe

-0.76

 reaſon

-0.74

 whoſe

-0.73

ſelf

-0.71

 himſelf

-0.70

POSITIVE LOGITS

 including

1.37

 Including

1.25

INCLUDING

1.23

including

1.22

Including

1.19

 INCLUDING

1.15

 waaronder

1.09

 включая

1.05

 einschließlich

1.04

Includes

1.03

Activations Density 0.151%

phrases that involve the concept of inclusion or factors from a list

No Comments

No Known Activations