INDEX

Explanations

phrases indicating a historical or chronological context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

前は

-0.55

ukunft

-0.49

￣)

-0.49

 deleteAll

-0.49

sphin

-0.48

UTELY

-0.48

ługość

-0.48

vs

-0.47

chọn

-0.47

سكر

-0.47

POSITIVE LOGITS

 newBuilder

0.83

 typelib

0.83

SourceChecksum

0.78

 Именно

0.72

OGND

0.72

 именно

0.72

InputBorder

0.71

 właśnie

0.70

GEBURTSDATUM

0.70

AndroidJUnit

0.69

Activations Density 0.156%

phrases indicating a historical or chronological context

No Comments

No Known Activations