INDEX

Explanations

the phrase "into" in various contexts

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

"into" followed by an article

np_acts-logits-general · gemini-2.0-flash

entry into states or contexts

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

 âgées

-0.65

 variés

-0.59

 deschis

-0.59

 correto

-0.58

 russes

-0.58

 paille

-0.56

 înainte

-0.56

 cuillère

-0.55

 pewno

-0.55

 françaises

-0.55

POSITIVE LOGITS

duced

0.84

 pinulongan

0.81

the

0.79

INTO

0.78

 adulthood

0.76

 INTO

0.76

Into

0.71

ConstraintMaker

0.69

xic

0.69

OGND

0.69

Activations Density 0.128%

the phrase "into" in various contexts

"into" followed by an article

entry into states or contexts

No Comments

No Known Activations