INDEX

Explanations

statements or claims related to terrorism and counter-terrorism efforts

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

testens

-0.49

 informasi

-0.48

 ciasc

-0.48

 verità

-0.45

none

-0.45

it

-0.45

ceği

-0.44

 akhirnya

-0.44

 nhờ

-0.44

 rafraî

-0.43

POSITIVE LOGITS

 citing

1.35

 pointing

1.34

 Referring

1.29

Referring

1.27

 stating

1.26

 referring

1.26

 saying

1.22

 stressing

1.18

Saying

1.15

 mentioning

1.14

Activations Density 0.192%

statements or claims related to terrorism and counter-terrorism efforts

No Comments

No Known Activations