INDEX

Explanations

concepts related to technology and media

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

punctuation and question marks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.67

 CreateTagHelper

-0.63

AddTagHelper

-0.62

pareja

-0.62

 autorytatywna

-0.60

XmlAccessType

-0.60

DockStyle

-0.59

MigrationBuilder

-0.59

 الحره

-0.59

hyrchwyd

-0.59

POSITIVE LOGITS

0.84

!!!

0.58

!”

0.58

?!

0.58

!)

0.56

!!

0.55

!?

0.55

!"

0.54

!!!!

0.54

!),

0.54

Activations Density 0.053%

concepts related to technology and media

punctuation and question marks

No Comments

No Known Activations