INDEX

Explanations

details and specifications of items

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

weight, yield, numbers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

⤹

-0.60

utilisons

-0.55

 Савезне

-0.55

RectangleBorder

-0.54

httphttps

-0.53

Tikang

-0.47

 صوتيه

-0.46

GraphicsUnit

-0.46

COUVER

-0.44

تقاوى

-0.43

POSITIVE LOGITS

richTextPanel

0.43

createTextNode

0.41

ModelAdmin

0.41

MS

0.40

 Mark

0.39

eye

0.38

 disque

0.38

ISupport

0.37

 natin

0.36

 disk

0.36

Activations Density 0.007%

details and specifications of items

weight, yield, numbers

No Comments

No Known Activations