INDEX

Explanations

mentions of email addresses or usernames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

出版年

-0.52

scienced

-0.43

 phóng

-0.42

GA

-0.40

 edili

-0.37

 plass

-0.36

 pisang

-0.36

 consistent

-0.36

洲

-0.35

DecimalFormat

-0.35

POSITIVE LOGITS

клопе

0.92

 <<<<<<<<<<<<<<

0.82

CopyWith

0.81

parsedMessage

0.79

zarchiwizowane

0.77

StoryboardSegue

0.76

SharedDtor

0.76

 vans

0.75

Hochspringen

0.73

vertisement

0.72

Activations Density 0.221%

mentions of email addresses or usernames

No Comments

No Known Activations