INDEX

Explanations

prompts to take action, particularly clicking links or images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 المعيارى

-0.66

aarrggbb

-0.65

المناصب

-0.61

Дереккөздер

-0.53

 الحره

-0.50

 otomatig

-0.49

хьтан

-0.47

memoized

-0.47

else

-0.47

ELSE

-0.47

POSITIVE LOGITS

bait

0.84

ety

0.71

 مشين

0.66

 anywhere

0.64

 hereto

0.60

ReusableCell

0.58

 play

0.55

 bait

0.54

 thumbnails

0.54

Bait

0.54

Activations Density 0.122%

prompts to take action, particularly clicking links or images

No Comments

No Known Activations