INDEX

Explanations

the word "the" and words that often appear close to it.

oai_token-act-pair · gemini-2.0-flash

nominal phrases related to locations or attributes

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

the

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

IBOutlet

-0.79

 الحره

-0.72

ביוגרפיה

-0.67

 للاسماء

-0.67

новништво

-0.64

AutoresizingMask

-0.62

SharedCtor

-0.57

 ویکی‌پدیای

-0.57

 محفوظة

-0.56

CompleteListener

-0.55

POSITIVE LOGITS

 front

0.60

]';

0.56

 lake

0.56

 autorytatywna

0.53

 shed

0.52

出版年

0.52

 assigned

0.52

zoo

0.51

 local

0.50

 nearest

0.50

Activations Density 0.835%

the word "the" and words that often appear close to it.

nominal phrases related to locations or attributes

the

No Comments

No Known Activations