INDEX

Explanations

intensifiers that amplify descriptions or attributes

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

ded

-0.67

Griffin

-0.66

id

-0.66

 проще

-0.66

 برانيه

-0.65

 Jackman

-0.64

zkod

-0.64

filepath

-0.63

 Akhtar

-0.63

 reclama

-0.62

POSITIVE LOGITS

 very

1.30

 Very

1.26

 VERY

1.25

VERY

1.25

Very

1.24

very

1.23

sehr

1.01

Molto

0.94

muy

0.92

 très

0.92

Activations Density 0.060%

intensifiers that amplify descriptions or attributes

No Comments

No Known Activations