INDEX

Explanations

intensifiers or modifiers, specifically the word "very."

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

IsContent

-0.79

 проще

-0.69

 Akhtar

-0.68

id

-0.67

 ombre

-0.67

 Jackman

-0.67

ded

-0.67

 forthwith

-0.66

 برانيه

-0.66

Griffin

-0.65

POSITIVE LOGITS

 very

1.76

Very

1.60

 Very

1.60

very

1.57

VERY

1.50

 VERY

1.49

 très

1.19

 sehr

1.19

muy

1.18

sehr

1.18

Activations Density 0.069%

intensifiers or modifiers, specifically the word "very."

No Comments

No Known Activations