INDEX

Explanations

references to medical or legal professionals, particularly their titles and degrees

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

 صوتيه

-0.71

...

-0.48

>())

-0.47

 ''),

-0.47

}],

-0.46

 either

-0.45

mişti

-0.45

the

-0.44

miyor

-0.44

 missão

-0.44

POSITIVE LOGITS

contentLoaded

1.10

+#+

0.95

Vidite

0.84

ArgsConstructor

0.80

Efq

0.76

Tikang

0.72

[++

0.72

 useStyles

0.72

 createSprite

0.71

 Wikimedijinoj

0.68

Activations Density 0.153%

references to medical or legal professionals, particularly their titles and degrees

No Comments

No Known Activations