INDEX

Explanations

phrases related to user rights and responsibilities in various contexts

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

 Prise

-0.49

umenti

-0.46

åde

-0.45

atimes

-0.45

DEO

-0.44

 Pris

-0.44

ban

-0.44

 Manas

-0.44

SetInt

-0.44

Ban

-0.43

POSITIVE LOGITS

 bénéficie

0.92

 benefit

0.90

 receives

0.90

 enjoy

0.90

 receive

0.84

 enjoys

0.81

benefit

0.81

 bénéficient

0.81

 hoeft

0.80

 benefited

0.79

Activations Density 0.474%

phrases related to user rights and responsibilities in various contexts

No Comments

No Known Activations