INDEX

Explanations

patterns of numerical data and their contextual relevance in text

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

And

-0.51

-0.50

-0.49

-0.48

->

-0.47

-0.46

-0.45

 short

-0.45

and

-0.44

POSITIVE LOGITS

IVEREF

0.90

ьаж

0.87

 Савезне

0.83

OGND

0.82

ReusableCell

0.79

ViewFeatures

0.78

UnusedPrivate

0.78

 defaultstate

0.76

RegistryLite

0.75

 nahilalakip

0.75

Activations Density 0.047%

patterns of numerical data and their contextual relevance in text

No Comments

No Known Activations