INDEX

Explanations

phrases and words related to safety and health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

VersionUID

-0.64

 InputDecoration

-0.62

ίδι

-0.57

AIRE

-0.56

WebControls

-0.56

kespeare

-0.54

zkiem

-0.54

ZZI

-0.52

 table

-0.52

POSITIVE LOGITS

Therefore

0.57

RegressionTest

0.55

хьтан

0.55

 Therefore

0.54

PreferredItem

0.54

كذا

0.52

imanapun

0.52

 <=",

0.52

BeginContext

0.51

 <>",

0.49

Activations Density 0.046%

phrases and words related to safety and health conditions

No Comments

No Known Activations