INDEX

Explanations

verbs and phrases associated with actions and their effectiveness

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

"do" followed by a negative word

np_acts-logits-general · gemini-2.0-flash

do not / do nothing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 متعلقه

-0.70

<bos>

-0.67

Portail

-0.66

 HasFactory

-0.63

TagHelpers

-0.63

AutoScale

-0.62

 useAppContext

-0.62

awtextra

-0.62

Cyfeiriadau

-0.60

 الحره

-0.60

POSITIVE LOGITS

 justice

0.68

 little

0.62

 away

0.61

 violence

0.61

 credit

0.60

 nothing

0.58

 wonders

0.54

violence

0.53

oming

0.53

 harm

0.51

Activations Density 0.130%

verbs and phrases associated with actions and their effectiveness

"do" followed by a negative word

do not / do nothing

No Comments

No Known Activations