INDEX

Explanations

conditional phrases that express uncertainty or hypothetical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ویکی‌پدیای

-0.81

contentLoaded

-0.72

ioutil

-0.71

 houſe

-0.70

SAK

-0.69

 Kanu

-0.67

 Hotspur

-0.65

 Celia

-0.64

WriteLiteral

-0.64

 Mako

-0.63

POSITIVE LOGITS

it

0.67

 though

0.60

 they

0.59

guh

0.56

iculous

0.54

cutta

0.54

 Picchu

0.54

 jButton

0.52

guigu

0.51

VIATIONS

0.51

Activations Density 0.077%

conditional phrases that express uncertainty or hypothetical situations

No Comments

No Known Activations