INDEX

Explanations

expressions related to living conditions and experiences

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

Mentions the state of being alive

np_acts-logits-general · gemini-2.0-flash

lived, lives, living in

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

bootstrapcdn

-0.84

WebControls

-0.72

 Samaria

-0.68

IUrlHelper

-0.67

UVWXYZ

-0.65

 nonatomic

-0.64

argout

-0.62

SpringBootTest

-0.62

ioutil

-0.61

 Catawiki

-0.61

POSITIVE LOGITS

 lived

0.67

 vidas

0.65

 lives

0.65

 life

0.57

 Lived

0.55

 חיים

0.53

Living

0.52

 living

0.52

 LIVING

0.50

lives

0.50

Activations Density 0.062%

expressions related to living conditions and experiences

Mentions the state of being alive

lived, lives, living in

No Comments

No Known Activations