INDEX

Explanations

expressions of belief and conviction

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

"believe" or "believed"

np_acts-logits-general · gemini-2.0-flash

believe me

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 оригіналу

-0.71

gdx

-0.70

TagHelpers

-0.69

 kaynağından

-0.65

ContentAsync

-0.64

="">

-0.64

XmlAccessorType

-0.62

displayquote

-0.60

SourceChecksum

-0.60

atimes

-0.59

POSITIVE LOGITS

 BELIEVE

1.01

 believe

0.98

 strongly

0.96

believe

0.95

Believe

0.93

 Believe

0.92

 believes

0.91

 myſelf

0.85

 Beliefs

0.84

 croy

0.83

Activations Density 0.071%

expressions of belief and conviction

"believe" or "believed"

believe me

No Comments

No Known Activations