INDEX

Explanations

punctuation, specifically commas

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

 undertaking

-0.55

evich

-0.54

Regressor

-0.53

rown

-0.52

خاص

-0.49

気を

-0.47

legung

-0.47

DV

-0.46

دين

-0.46

ær

-0.46

POSITIVE LOGITS

AndroidJUnit

0.82

دانشنامهٔ

0.82

GOTREF

0.82

__":

0.73

Gemeinden

0.73

thâu

0.70

 uuidv

0.70

Tembelea

0.69

❶

0.69

äksi

0.69

Activations Density 0.425%

punctuation, specifically commas

No Comments

No Known Activations