INDEX

Explanations

terms indicating collective identity or inclusivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

境的

-0.68

先の

-0.66

});

-0.66

:'/

-0.65

 @"";

-0.65

ないで

-0.63

先に

-0.63

an

-0.62

vos

-0.62

σ

-0.61

POSITIVE LOGITS

 everyone

2.34

everyone

2.29

Everyone

2.21

 Everyone

2.21

 everybody

2.17

everybody

2.14

 Everybody

2.10

 EVERYONE

2.04

Everybody

2.04

everything

1.57

Activations Density 0.033%

terms indicating collective identity or inclusivity

No Comments

No Known Activations