INDEX

Explanations

phrases related to objectives or purposes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lapsingToolbar

-0.87

Geplaatst

-0.58

 تضيفلها

-0.56

 Wikimedijinoj

-0.51

 itſelf

-0.50

Ữ

-0.49

Còn

-0.49

 الميل

-0.49

 StringTokenizer

-0.48

zką

-0.47

POSITIVE LOGITS

 which

2.60

which

1.96

 Which

1.95

Which

1.89

 WHICH

1.82

 whom

1.70

 whereof

1.62

 duquel

1.47

 которого

1.43

 которых

1.41

Activations Density 0.266%

phrases related to objectives or purposes in various contexts

No Comments

No Known Activations