INDEX

Explanations

instances of the word "write" and its variations

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

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

 resourceCulture

-0.66

বহ

-0.54

favicon

-0.53

 Produits

-0.50

ctools

-0.50

contentLoaded

-0.50

RTEX

-0.48

DockStyle

-0.47

 Mila

-0.47

ldquo

-0.47

POSITIVE LOGITS

 write

0.74

 Writes

0.70

 ulang

0.70

 Write

0.69

ंदीखरीदारी

0.69

 writers

0.69

 writes

0.69

 propOrder

0.67

 wrongs

0.67

writerow

0.65

Activations Density 0.198%

instances of the word "write" and its variations

No Comments

No Known Activations