INDEX

Explanations

phrases related to attribution and responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Efq

-0.66

 Monfieur

-0.65

 Majefty

-0.63

aigu

-0.57

 ſeveral

-0.56

 Produced

-0.55

 Conſ

-0.55

 Diſ

-0.54

 AssemblyTitle

-0.54

 Reſ

-0.54

POSITIVE LOGITS

 attributed

0.72

 link

0.63

 ascribe

0.60

 Link

0.58

endphp

0.56

linking

0.55

 linking

0.55

 ascribed

0.54

Setter

0.52

 attribute

0.52

Activations Density 0.396%

phrases related to attribution and responsibility

No Comments

No Known Activations