INDEX

Explanations

words related to processes, actions, and impacts, often within institutional or larger contexts

oai_token-act-pair · gemini-2.0-flash

instances of the word "of"

np_token-act-pair-logits · gpt-4o-mini

a topic or process

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ⓧ

-0.81

TagHelper

-0.81

 "..\..\

-0.80

脚注の使い方

-0.73

//

-0.59

 "..\..\..\

-0.59

évaluateur

-0.58

lgari

-0.57

tabilis

-0.57

lapsible

-0.57

POSITIVE LOGITS

of

1.44

 của

0.72

ของ

0.66

 של

0.56

of

0.49

userdetails

0.46

 igång

0.45

 ofre

0.45

 schéma

0.44

 ของ

0.44

Activations Density 16.414%

words related to processes, actions, and impacts, often within institutional or larger contexts

instances of the word "of"

a topic or process

No Comments

No Known Activations