INDEX

Explanations

instances of code or programming-related terms

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

 itſelf

-0.77

 gundam

-0.66

 themſelves

-0.66

 elastici

-0.64

 fign

-0.64

 doubtnut

-0.63

 Italijanski

-0.63

 handker

-0.63

〗

-0.62

!")

-0.61

POSITIVE LOGITS

onViewCreated

0.57

my

0.53

 CURIAM

0.50

Jäh

0.49

@__

0.49

rasing

0.49

ody

0.49

awtextra

0.47

čnosti

0.47

æa

0.46

Activations Density 0.159%

instances of code or programming-related terms

No Comments

No Known Activations