INDEX

Explanations

phrases related to suppression and inhibition

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

Dok

-0.71

 Peter

-0.68

Dok

-0.68

 Beek

-0.67

ek

-0.66

 تط

-0.64

ⓧ

-0.63

-0.62

 Kinder

-0.62

Peter

-0.60

POSITIVE LOGITS

 suppress

1.63

 Suppression

1.54

SUP

1.49

SUP

1.48

 suppression

1.46

Sup

1.44

 suppresses

1.43

 suppressed

1.42

 suppressor

1.40

 Supp

1.38

Activations Density 0.200%

phrases related to suppression and inhibition

No Comments

No Known Activations