INDEX

Explanations

the word "as" and its variations in different contexts

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

fvar

-0.57

ธอ

-0.53

!("{}",

-0.51

traceback

-0.50

 BioLib

-0.49

Zitat

-0.48

 οποία

-0.48

 ſta

-0.48

րջ

-0.47

IntegerField

-0.46

POSITIVE LOGITS

as

0.93

HasAnnotation

0.68

As

0.67

 part

0.67

 autorytatywna

0.67

 ως

0.67

 समीक्षाएं

0.65

 opposed

0.65

作為

0.64

 ExecuteAsync

0.63

Activations Density 0.284%

the word "as" and its variations in different contexts

No Comments

No Known Activations