INDEX

Explanations

expressions of knowledge or awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

幸いです

-0.73

dhist

-0.67

 Gill

-0.67

 Efforts

-0.65

 Phelps

-0.63

 Morris

-0.62

feu

-0.61

 mengel

-0.61

Pal

-0.61

WriteTagHelper

-0.60

POSITIVE LOGITS

 know

1.34

 knows

1.33

know

1.32

Know

1.32

 Know

1.31

KNOW

1.30

 KNOW

1.29

 Knows

1.29

 Knowles

1.23

knows

1.23

Activations Density 0.093%

expressions of knowledge or awareness

No Comments

No Known Activations