INDEX

Explanations

the letter 'i' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tonsoft

-0.57

 configureStore

-0.52

))=\

-0.50

openqa

-0.50

RTLD

-0.50

Kjelder

-0.47

IsContent

-0.47

 Administrativna

-0.47

odeficiency

-0.47

 disambiguazione

-0.46

POSITIVE LOGITS

awtextra

0.67

 CreateTagHelper

0.63

EndContext

0.63

CloseOperation

0.63

ReusableCell

0.60

BagLayout

0.59

apunov

0.59

 Exacts

0.58

 Avid

0.56

enumii

0.56

Activations Density 0.075%

the letter 'i' in various contexts

No Comments

No Known Activations