INDEX

Explanations

occurrences of the word "from."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 rospy

-0.56

 они

-0.55

깐

-0.51

 bezeichneter

-0.47

 вони

-0.47

 вона

-0.45

 он

-0.44

 він

-0.44

 она

-0.44

keep

-0.43

POSITIVE LOGITS

 afar

1.38

 whence

1.17

 within

1.16

 scratch

1.14

 across

1.10

within

1.10

 abroad

1.06

 elsewhere

1.02

the

1.01

 segi

0.98

Activations Density 0.271%

occurrences of the word "from."

No Comments

No Known Activations