INDEX

Explanations

the word "into"

oai_token-act-pair · gemini-2.0-flash

into

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 tartalomajánló

-1.22

 into

-1.14

 typelib

-1.13

 Paglinawan

-1.08

verwijspagina

-1.06

principalTable

-1.02

 Into

-0.99

QMetaType

-0.97

Into

-0.93

ніципа

-0.91

POSITIVE LOGITS

0.57

0.54

 OnInit

0.54

0.53

ty

0.53

tv

0.48

on

0.47

men

0.47

Activations Density 1.643%

the word "into"

into

No Comments

No Known Activations

the word "into"

into

No Comments

No Known Activations