INDEX

Explanations

phrases that express disagreement or differing opinions

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

Inside parentheses

np_acts-logits-general · gemini-2.0-flash

(`

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

:]:

-0.56

WebServlet

-0.54

readyState

-0.52

ITECH

-0.51

Grath

-0.51

Survival

-0.50

 survival

-0.49

getColumnIndex

-0.49

writeFieldEnd

-0.48

 jeugd

-0.47

POSITIVE LOGITS

Répondre

0.63

">//

0.61

 Reply

0.60

 comments

0.58

 Normdatei

0.57

 Réponses

0.56

Reply

0.56

Comments

0.56

 Comments

0.56

berdayakan

0.55

Activations Density 0.040%

phrases that express disagreement or differing opinions

Inside parentheses

(`

No Comments

No Known Activations