INDEX

Explanations

dialogue and interactions between characters

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

Quoted dialogue beginnings

np_acts-logits-general · gemini-2.0-flash

dialogue starts

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

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

expandindo

-0.72

PMailer

-0.69

WebElementEntity

-0.60

"}")

-0.57

ViewChild

-0.52

!).

-0.51

Omg

-0.51

 !!!!!!

-0.50

 lenker

-0.50

PMID

-0.49

POSITIVE LOGITS

Tch

0.69

 Looks

0.60

ροφο

0.60

othesis

0.60

 Listen

0.58

Looks

0.57

Look

0.57

 Look

0.57

 Guess

0.57

look

0.56

Activations Density 0.103%

dialogue and interactions between characters

Quoted dialogue beginnings

dialogue starts

No Comments

No Known Activations