INDEX

Explanations

instances of punctuation and symbols that indicate conversation or questioning

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

 gynhyrchwyd

-0.65

MLLoader

-0.59

 alturas

-0.50

 BorderSide

-0.49

elcome

-0.49

 förstå

-0.48

InputTagHelper

-0.48

 rire

-0.47

 Hongrie

-0.47

 informée

-0.47

POSITIVE LOGITS

ANTLR

0.69

StoryboardSegue

0.63

 JADX

0.62

 dovuto

0.59

AndEndTag

0.59

 שוליים

0.58

Décès

0.58

InjectAttribute

0.56

 StatefulWidget

0.56

 Pingback

0.56

Activations Density 0.630%

instances of punctuation and symbols that indicate conversation or questioning

No Comments

No Known Activations