INDEX

Explanations

phrases that signal comparison or similarity

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

"Like" starts the sentence

np_acts-logits-general · gemini-2.0-flash

making comparisons

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

'}';

-0.59

 considérons

-0.59

se

-0.58

apyrus

-0.54

 ISNI

-0.54

es

-0.53

!("{

-0.52

en

-0.52

zer

-0.52

ES

-0.52

POSITIVE LOGITS

liest

0.89

 LIKE

0.88

lihood

0.86

LIKE

0.83

 minded

0.83

เดียว

0.82

wiſe

0.82

WISE

0.78

lier

0.76

like

0.75

Activations Density 0.108%

phrases that signal comparison or similarity

"Like" starts the sentence

making comparisons

No Comments

No Known Activations