INDEX

Explanations

references to locations in Washington state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

الدراسه

-0.47

Func

-0.46

rimid

-0.43

빨

-0.42

cip

-0.40

ż

-0.39

sav

-0.39

жно

-0.38

...

-0.38

ның

-0.38

POSITIVE LOGITS

 Seattle

1.13

COUVER

1.11

Seattle

1.11

 Puget

1.02

seattle

0.93

 Spokane

0.92

 Vancouver

0.91

 Rainier

0.91

 Tacoma

0.90

 Yakima

0.87

Activations Density 1.146%

references to locations in Washington state

No Comments

No Known Activations