INDEX

Explanations

occurrences of the word "make."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 grand

-0.53

writeFieldEnd

-0.53

flo

-0.51

pos

-0.49

sal

-0.49

 common

-0.49

-0.48

Viitteet

-0.47

“

-0.46

POSITIVE LOGITS

Make

1.32

make

1.30

 makeup

1.23

 MAKE

1.23

 Make

1.21

 make

1.16

makeup

1.09

MAKE

1.06

 Makeup

1.05

Makeup

1.00

Activations Density 0.115%

occurrences of the word "make."

No Comments

No Known Activations