INDEX

Explanations

specific symbols or characters that may represent special formatting or units in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 defStyle

-0.71

تقاوى

-0.70

Rhestr

-0.65

 FetchType

-0.61

endpush

-0.59

 ddelweddau

-0.59

 endblock

-0.58

hassee

-0.58

 alluminio

-0.58

cookieParser

-0.58

POSITIVE LOGITS

<td>

0.52

 betweenstory

0.51

ConstraintMaker

0.50

">//

0.48

 almost

0.46

 nearly

0.44

तान

0.43

จัก

0.42

 goodness

0.41

BeginContext

0.41

Activations Density 0.327%

specific symbols or characters that may represent special formatting or units in data

No Comments

No Known Activations