INDEX

Explanations

words and phrases related to feelings, beliefs and opinions

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.65

 typelib

-0.60

 oleh

-0.54

 propOrder

-0.54

BeginInit

-0.51

发表于

-0.50

awtextra

-0.47

 الحره

-0.46

zug

-0.45

 onOptions

-0.43

POSITIVE LOGITS

uña

0.69

leştir

0.64

Palmar

0.63

rawDesc

0.61

yourself

0.61

lardır

0.60

triangleq

0.60

 yourself

0.60

eddable

0.60

 useState

0.59

Activations Density 0.700%

words and phrases related to feelings, beliefs and opinions

No Comments

No Known Activations