INDEX

Explanations

words that describe actions or states of being, particularly those related to creation, selection, and modification.

oai_token-act-pair · gemini-2.0-flash

Creation actions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Theſe

-0.67

 IBRARY

-0.62

出版年

-0.62

 ſhall

-0.59

continence

-0.59

 ſmall

-0.59

 NDEBUG

-0.59

IBLIO

-0.57

 himſelf

-0.56

 BRARY

-0.54

POSITIVE LOGITS

to

0.73

 with

0.69

WireFormatLite

0.60

off

0.58

SequentialGroup

0.56

日閲覧

0.55

awaiter

0.55

by

0.55

for

0.55

in

0.55

Activations Density 7.756%

words that describe actions or states of being, particularly those related to creation, selection, and modification.

Creation actions

No Comments

No Known Activations