INDEX

Explanations

references to restaurants and food-related experiences

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

Followed by prepositions or conjunctions

np_acts-logits-general · gemini-2.0-flash

bits and bobs

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

Xna

-0.64

fromnode

-0.63

WithIOException

-0.60

 kini

-0.58

IntoConstraints

-0.57

ⓧ

-0.56

 şimdi

-0.56

évaluateur

-0.55

ścić

-0.54

)}</

-0.53

POSITIVE LOGITS

 very

0.80

yorsunuz

0.77

Very

0.70

 nicely

0.67

 Very

0.66

very

0.66

 seemed

0.66

 excellent

0.65

 quite

0.65

 VERY

0.65

Activations Density 0.189%

references to restaurants and food-related experiences

Followed by prepositions or conjunctions

bits and bobs

No Comments

No Known Activations