INDEX

Explanations

instances of document format indicators

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.53

UBLIC

-0.47

 noDo

-0.46

-0.45

хнет

-0.43

"})

-0.43

">:

-0.42

 elämä

-0.42

 frattempo

-0.42

orithm

-0.41

POSITIVE LOGITS

#+#

0.92

BeginContext

0.70

出版年

0.69

ⓧ

0.69

LError

0.67

 مفص

0.66

 nahilalakip

0.65

$_['

0.64

 Италијани

0.64

يكب

0.64

Activations Density 2.167%

instances of document format indicators

No Comments

No Known Activations