INDEX

Explanations

phrases indicating the ability or permission to perform actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

OGND

-0.71

allow

-0.54

Provide

-0.50

Organisateur

-0.49

 jinak

-0.49

principalTable

-0.49

ressum

-0.46

क्षण

-0.46

offer

-0.46

redientes

-0.46

POSITIVE LOGITS

 download

0.80

 purchase

0.78

 either

0.71

 read

0.69

 TAMBIÉN

0.69

buy

0.67

 also

0.66

 view

0.66

 downloaded

0.64

 find

0.63

Activations Density 0.232%

phrases indicating the ability or permission to perform actions

No Comments

No Known Activations