INDEX

Explanations

references to influential figures or significant entities within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

})`

-0.49

 insuffisamment

-0.48

 ASSETS

-0.44

⤹

-0.44

UrlResolution

-0.44

 noDo

-0.42

astéroïdes

-0.42

mitives

-0.42

toprule

-0.41

onomies

-0.41

POSITIVE LOGITS

 StatefulWidget

0.50

 tartalomajánló

0.48

ceğine

0.44

verifyException

0.43



0.42

Espèce

0.40

addGroup

0.40

+#+#

0.38

URLException

0.36

(!__

0.36

Activations Density 0.096%

references to influential figures or significant entities within various contexts

No Comments

No Known Activations