INDEX

Explanations

phrases related to training and education processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

urlopen

-0.43

dowa

-0.40

رده

-0.39

ImageField

-0.39

*****

-0.38

 pris

-0.38

pic

-0.37

 Choice

-0.36

***

-0.36

Gamer

-0.36

POSITIVE LOGITS

 taught

1.08

 Taught

1.04

taught

1.04

 learnt

1.02

 mastering

1.01

learn

0.96

 imparare

0.96

 teaches

0.92

 learn

0.91

 Mastering

0.91

Activations Density 0.357%

phrases related to training and education processes

No Comments

No Known Activations