INDEX

Explanations

references to the color red and its various contexts and associations

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

"}")

-1.11

BibitemShut

-1.05

}%

-1.01

}`).

-1.01

 themſelves

-0.99

 jScrollPane

-0.98

✨:

-0.98

 myſelf

-0.96

.)}

-0.95

.}(

-0.95

POSITIVE LOGITS

Red

1.40

Red

1.39

RED

1.37

red

1.34

red

1.28

RED

1.25

红

1.12

 Reddy

1.04

 rosse

0.99

 Reds

0.98

Activations Density 0.076%

references to the color red and its various contexts and associations

No Comments

No Known Activations