INDEX

Explanations

mentions of the word "both."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Ver

-0.54

 favorite

-0.53

Ver

-0.51

ver

-0.50

mer

-0.49

seb

-0.49

TextAppearance

-0.48

 wanna

-0.48

pas

-0.47

sos

-0.47

POSITIVE LOGITS

 both

1.69

 både

1.50

both

1.50

 zowel

1.46

Both

1.38

 Both

1.31

 sowohl

1.27

 zarówno

1.20

tanto

1.18

 BOTH

1.17

Activations Density 0.146%

mentions of the word "both."

No Comments

No Known Activations