INDEX

Explanations

structures in programming or data management contexts

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

Bullet points or numbered lists

np_acts-logits-general · gemini-2.0-flash

list items and question marks

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Diwedd

-0.61

ῖς

-0.58

den

-0.57

sizeCache

-0.56

 confirmer

-0.56

紆

-0.54

السكان

-0.53

 hold

-0.53

={({

-0.53

GeneratedMessage

-0.52

POSITIVE LOGITS

item

0.88

itemize

0.75

ITEM

0.61

toxicity

0.61

 itemName

0.57

jspx

0.56

 newOwner

0.56

 referrerpolicy

0.55

ifrance

0.53

Wod

0.53

Activations Density 0.005%

structures in programming or data management contexts

Bullet points or numbered lists

list items and question marks

No Comments

No Known Activations