INDEX

Explanations

instances of the word "for" in a context that suggests action or purpose

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

 EconPapers

-0.56

 الفلسطينية

-0.53

 phase

-0.53

 date

-0.53

explique

-0.51

CWE

-0.50

 regular

-0.50

Nhap

-0.49

 Bapak

-0.49

 origen

-0.49

POSITIVE LOGITS

parsedMessage

0.64

RequestMapping

0.61

HtmlAttribute

0.61

inaison

0.57

arci

0.56

 eventdata

0.55

 useAppContext

0.54

 Expenditure

0.53

AnchorStyles

0.52

 Merdeka

0.52

Activations Density 0.059%

instances of the word "for" in a context that suggests action or purpose

No Comments

No Known Activations