INDEX

Explanations

sentences containing "I" and words associated with telling a story

oai_token-act-pair · gemini-2.0-flash

I

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

am

-0.69

AM

-0.61

mno

-0.60

asks

-0.59

am

-0.55

Am

-0.55

ami

-0.52

 myths

-0.52

écnicas

-0.51

 watches

-0.51

POSITIVE LOGITS

 ostavi

0.64

 casó

0.53

 MotionEvent

0.53

WriteTagHelper

0.52

 Waray

0.50

 AttributeSet

0.50

 yourself

0.49

AddTagHelper

0.49

 autorytatywna

0.47

 Мексичка

0.47

Activations Density 8.493%

sentences containing "I" and words associated with telling a story

I

No Comments

No Known Activations