INDEX

Explanations

references to different categories or classifications of items or concepts

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

omiast

-0.62

icin

-0.60

 Meksiku

-0.55

 beur

-0.54

esModule

-0.54

서는

-0.53

 OFDb

-0.52

jsxFileName

-0.52

 sés

-0.52

PageIndex

-0.50

POSITIVE LOGITS

of

1.34

 ―――――

0.67

extAlignment

0.65

 BoxFit

0.65

 itſelf

0.65

ècie

0.64

 myſelf

0.64

 løpet

0.63

 bunch

0.62

FontOfSize

0.62

Activations Density 0.531%

references to different categories or classifications of items or concepts

No Comments

No Known Activations