INDEX

Explanations

instances of the word "again" 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

ftagPool

-0.60

 kteří

-0.57

kano

-0.54

 []).

-0.52

ZI

-0.51

 useAppContext

-0.48

rainian

-0.47

 fact

-0.47

<?=$

-0.47

POSITIVE LOGITS

igshid

0.79

sidemargin

0.76

enumi

0.74

 <=",

0.71

 Paglinawan

0.71

ruptedException

0.68

HandlerContext

0.68

もや

0.67

yntaxException

0.67

 reiter

0.67

Activations Density 0.049%

instances of the word "again" and its variations

No Comments

No Known Activations