INDEX

Explanations

references to user-related information and actions within a programming or software context

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

ță

-0.55

The

-0.52

No

-0.49

-0.47

ereza

-0.46

さら

-0.45

 Finally

-0.45

さらに

-0.44

 than

-0.44

ể

-0.44

POSITIVE LOGITS

 purpoſe

0.78

 NDEBUG

0.75

 houſe

0.74

Билгалдахарш

0.73

 myſelf

0.73

 Савезне

0.70

 leaſt

0.68

NUMX

0.67

uſ

0.66

 decedent

0.65

Activations Density 0.143%

references to user-related information and actions within a programming or software context

No Comments

No Known Activations