INDEX

Explanations

time formats and related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

########.

-0.65

gdb

-0.60

BASEPATH

-0.54

rawDesc

-0.51

MessageTagHelper

-0.51

يميديا

-0.51

 ivelany

-0.50

inguish

-0.50

TagHelper

-0.50

ⓘ

-0.49

POSITIVE LOGITS

fillType

0.70

 thirty

0.62

انيف

0.59

AnchorStyles

0.57

 forty

0.56

PM

0.54

PM

0.52

 kém

0.52

thirty

0.52

μμ

0.51

Activations Density 0.333%

time formats and related elements

No Comments

No Known Activations