INDEX

Explanations

phrases related to the effects or impacts of various interventions or treatments

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

erialized

-0.47

 مست

-0.45

then

-0.44

porte

-0.43

 metter

-0.43

 resa

-0.43

し

-0.41

 entityManager

-0.41

 vostro

-0.41

liferay

-0.41

POSITIVE LOGITS

сылкі

1.05

effects

0.92

]")]

0.88

 wikipagina

0.85

)";

0.84

 Effects

0.82

Effects

0.80

stylers

0.80

 effects

0.80

effect

0.77

Activations Density 0.339%

phrases related to the effects or impacts of various interventions or treatments

No Comments

No Known Activations