INDEX

Explanations

words and phrases related to improvement and enhancement in contexts

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

followed by "the"

np_acts-logits-general · gemini-2.0-flash

increase, decrease, or expansion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

DataMember

-0.46

ノロ

-0.41

PreferredItem

-0.41

NewReader

-0.40

 vogliono

-0.40

/**

-0.40

ENARIO

-0.39

こ

-0.39

 anything

-0.39

 partidas

-0.39

POSITIVE LOGITS

ValueStyle

0.82

the

0.75

fillType

0.75

MessageTagHelper

0.69

 opportunities

0.68

 overall

0.67

Portail

0.67

overall

0.66

 bestehende

0.66

Demikian

0.66

Activations Density 0.573%

words and phrases related to improvement and enhancement in contexts

followed by "the"

increase, decrease, or expansion

No Comments

No Known Activations