INDEX

Explanations

uses of first-person pronouns and related verbs

oai_token-act-pair · gemini-2.0-flash

I/my

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

aarrggbb

-0.67

Portály

-0.65

WriteLiteral

-0.59

LEncoder

-0.57

 دیکھیے

-0.56

 standing

-0.55

 testify

-0.55

fieldId

-0.54

 CreateTagHelper

-0.54

<bos>

-0.54

POSITIVE LOGITS

 mourut

0.47

 sconfit

0.47

 obicei

0.45

 eccell

0.45

XmlElement

0.45

ámico

0.44

quartered

0.44

unchecked

0.44

 játé

0.42

ajur

0.42

Activations Density 10.268%

uses of first-person pronouns and related verbs

I/my

No Comments

No Known Activations